Prof Ioannis Patras

Ioannis Patras

Professor of Computer Vision and Human Sensing
Head of The Centre for Multimodal AI

School of Electronic Engineering and Computer Science
Queen Mary University of London
www.eecs.qmul.ac.uk/people/profiles/patrasioannis.html
Centre for Multimodal AI
ORCID Scopus Google Scholar LinkedIn

Research

Computer Vision, Machine Learning, Multimodal AI, Affective Computing, NLP

Interests

My expertise is in the area of Computer Vision and Machine learning with applications in Multimedia
Analysis and Affective Computing. My recent works and research interests are at the cross-roads of
Computer Vision and NLP designing methods for both recognition and controllable generation. My aspiration is to contribute to research towards AI systems that serve the greater good.

Publications

solid heart iconPublications of specific relevance to the Centre for Multimodal AI

2024

Relevant PublicationEfficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing
Maniadis Metaxas I, Tzimiropoulos G and Patras I
Lecture Notes in Computer Science, Springer Nature vol. 15090, 436-454.  
23-11-2024
Relevant PublicationIntroduction to the Special Issue on Realistic Synthetic Data: Generation, Learning, Evaluation
Ionescu B, Patras I, Müller H and Del Bimbo A
Acm Transactions On Multimedia Computing Communications and Applications, Association For Computing Machinery (Acm) 
09-11-2024
bullet iconBilinear Models of Parts and Appearances in Generative Adversarial Networks
Oldfield J, Tzelepis C, Panagakis Y, Nicolaou MA and Patras I
Ieee Transactions On Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers (Ieee) vol. 46 (12), 8568-8579.  
06-11-2024
Relevant PublicationCLIPCleaner: Cleaning Noisy Labels with CLIP
Feng C, Tzimiropoulos G and Patras I
Proceedings of the 32nd ACM International Conference on Multimedia., 876-885.  
28-10-2024
Relevant PublicationMultilinear Mixture of Experts: Scalable Expert Specialization through Factorization
Oldfield J, Georgopoulos M, Chrysos G, Tzelepis C, Panagakis Y, Nicolaou MA, Deng J and Patras I
 
16-10-2024
bullet iconEfficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing
Maniadis Metaxas I, Tzimiropoulos G and Patras I
European Conference on Computer Vision 2024 29 Sep 2024 - 4 Oct 2024. 
29-09-2024
Relevant PublicationOne-Shot Neural Face Reenactment via Finding Directions in GAN's Latent Space.
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
Int. J. Comput. Vis. vol. 132, 3324-3354.  
01-08-2024
bullet iconNoiseBox: Towards More Efficient and Effective Learning with Noisy Labels
Feng C, Tzimiropoulos G and Patras I
Ieee Transactions On Circuits and Systems For Video Technology, Institute of Electrical and Electronics Engineers 
11-07-2024
Relevant PublicationExplainable Video Summarization for Advancing Media Content Production
Apostolidis E, Balaouras G, Patras I and Mezaris V
In Encyclopedia of Information Science and Technology, Sixth Edition, Igi Global 1-24.  
01-07-2024
bullet iconEmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition
Foteinopoulou NM and Patras I
, Institute of Electrical and Electronics Engineers (Ieee) vol. 00, 1-10.  
31-05-2024
bullet iconFOAA: Flattened Outer Arithmetic Attention for Multimodal Tumor Classification
Alwazzan O, Patras I and Slabaugh G
International Symposium On Biomedical Imaging, Institute of Electrical and Electronics Engineers (Ieee) vol. 00, 1-5.  
30-05-2024
Relevant PublicationEnhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer
Zhao Z, Cao Y, Gong S and Patras I
 
29-05-2024
bullet iconMotor Imagery Decoding Using Ensemble Curriculum Learning and Collaborative Training
Zoumpourlis G and Patras I
12th International Winter Conference on Brain-Computer Interface (BCI) 26 Feb 2024 - 28 Feb 2024. 
02-04-2024
bullet iconDiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
 
25-03-2024
bullet iconOne-Shot Neural Face Reenactment via Finding Directions in GAN’s Latent Space
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
International Journal of Computer Vision, Springer Nature vol. 132 (8), 3324-3354.  
13-03-2024
bullet iconMotor Imagery Decoding Using Ensemble Curriculum Learning and Collaborative Training
Zoumpourlis G and Patras I
, Institute of Electrical and Electronics Engineers (Ieee) vol. 00, 1-8.  
28-02-2024
bullet iconImproving Fairness using Vision-Language Driven Image Augmentation
D’Incà M, Tzelepis C, Patras I and Sebe N
, Institute of Electrical and Electronics Engineers (Ieee) vol. 00, 4683-4692.  
08-01-2024
bullet iconSelf-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features
Gao Z, Feng C and Patras I
2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). vol. 00, 1762-1772.  
08-01-2024
Relevant PublicationFOAA: Flattened Outer Arithmetic Attention for Multimodal Tumor Classification.
Alwazzan O, Patras I and Slabaugh GG
ISBI., 1-5.  
01-01-2024
Relevant PublicationGet Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization.
Zhang Z, Liu Z and Patras I
Corr vol. abs/2408.04983 
01-01-2024
Relevant PublicationAre CLIP features all you need for Universal Synthetic Image Origin Attribution?
Cioni D, Tzelepis C, Seidenari L and Patras I
Corr vol. abs/2408.09153 
01-01-2024
Relevant PublicationCemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition.
Sun Z, Song S, Patras I and Tzimiropoulos G
CoRR. vol. abs/2409.18876 
01-01-2024
Relevant PublicationSelf-Supervised Facial Representation Learning with Facial Region Awareness.
Gao Z and Patras I
CVPR., 2081-2092.  
01-01-2024
Relevant PublicationLAFS: Landmark-Based Facial Self-Supervised Learning for Face Recognition.
Sun Z, Feng C, Patras I and Tzimiropoulos G
CVPR., 1639-1649.  
01-01-2024
Relevant PublicationMM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance.
Meng D, Tzelepis C, Patras I and Tzimiropoulos G
Corr vol. abs/2409.11010 
01-01-2024
Relevant PublicationCLIPCleaner: Cleaning Noisy Labels with CLIP.
Feng C, Tzimiropoulos G and Patras I
ACM Multimedia., 876-885. Editors: Cai J, Kankanhalli MS, Prabhakaran B, Boll S, Subramanian R, Zheng L, Singh VK, César P, Xie L and Xu D. 
01-01-2024
Relevant PublicationSelf-Supervised Facial Representation Learning with Facial Region Awareness
Gao Z and Patras I
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 2081-2092.  
01-01-2024
Relevant PublicationLAFS: Landmark-Based Facial Self-Supervised Learning for Face Recognition
Sun Z, Feng C, Patras I and Tzimiropoulos G
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 1639-1649.  
01-01-2024
Relevant PublicationMultilinear Mixture of Experts: Scalable Expert Specialization through Factorization.
Oldfield J, Georgopoulos M, Chrysos GG, Tzelepis C, Panagakis Y, Nicolaou MA, Deng J and Patras I
Corr vol. abs/2402.12550 
01-01-2024
Relevant PublicationMOAB: Multi-Modal Outer Arithmetic Block For Fusion Of Histopathological Images And Genetic Data For Brain Tumor Grading.
Alwazzan O, Khan A, Patras I and Slabaugh GG
Corr vol. abs/2403.06349 
01-01-2024
Relevant PublicationImproving Fairness using Vision-Language Driven Image Augmentation.
D'Incà M, Tzelepis C, Patras I and Sebe N
WACV., 4683-4692.  
01-01-2024
Relevant PublicationVLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning.
Xenos A, Foteinopoulou NM, Ntinou I, Patras I and Tzimiropoulos G
Corr vol. abs/2404.07078 
01-01-2024
Relevant PublicationFashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion.
Singh AK and Patras I
Corr vol. abs/2404.18591 
01-01-2024

2023

Relevant PublicationA Study on the Use of Attention for Explaining Video Summarization
Apostolidis E, Mezaris V and Patras I
Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos., 41-49.  
29-10-2023
Relevant PublicationNarSUM 2023 Chairs Welcome
Kankanhalli MS, Patras I, Liu J, Wong Y and Komamizu T
Narsum 2023 - Proceedings of The 2nd Workshop On User-Centric Narrative Summarization of Long Videos, Co-Located With: Mm 2023 
29-10-2023
Relevant PublicationNarSUM '23: The 2nd Workshop on User-Centric Narrative Summarization of Long Videos
Kankanhalli MS, Patras I, Liu J, Wong Y, Komamizu T, Yamazaki S, Stephen K and Kansal K
Proceedings of the 31st ACM International Conference on Multimedia., 9731-9733.  
26-10-2023
bullet iconEmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition
Foteinopoulou NM and Patras I
 
25-10-2023
Relevant PublicationSelecting A Diverse Set Of Aesthetically-Pleasing and Representative Video Thumbnails Using Reinforcement Learning
Apostolidis E, Balaouras G, Mezaris V and Patras I
2023 IEEE International Conference on Image Processing (ICIP). vol. 00, 2460-2464.  
11-10-2023
Relevant PublicationHyperReenact: one-shot reenactment via jointly learning to refine and retarget faces
Bounareli S, TZELEPIS C, Argyriou V, Patras I and Tzimiropoulos G
International Conference on Computer Vision. 
02-10-2023
Relevant PublicationSelf-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features
Gao Z, Feng C and Patras I
 
25-08-2023
Relevant PublicationPrompting Visual-Language Models for Dynamic Facial Expression Recognition
Zhao Z and Patras I
 
25-08-2023
Relevant PublicationSelf-Supervised Video Similarity Learning
Kordopatis-Zilos G, Tolias G, Tzelepis C, Kompatsiaris I, Patras I and Papadopoulos S
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). vol. 00, 4756-4766.  
24-06-2023
Relevant PublicationAttribute-Preserving Face Dataset Anonymization via Latent Code Optimization
Barattin S, Tzelepis C, Patras I and Sebe N
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). vol. 00, 8001-8010.  
24-06-2023
Relevant PublicationMaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset
Feng C and Patras I
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). vol. 00, 19913-19922.  
24-06-2023
Relevant PublicationDivClust: Controlling Diversity in Deep Clustering
Maniadis Metaxas I, Tzimiropoulos G and Patras I
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023. 
18-06-2023
Relevant PublicationControllable image generation and manipulation
Patras I
Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation., 1-1.  
12-06-2023
Relevant PublicationMOAB: Multi-Modal Outer Arithmetic Block for Fusion of Histopathological Images and Genetic Data for Brain Tumor Grading
Alwazzan O, Khan A, Patras I and Slabaugh G
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). vol. 00, 1-5.  
21-04-2023
Relevant PublicationJust To See You Smile: SMILEY, a Voice-Guided GUY GAN
Yang Q, Tzelepis C, Nikolenko S, Patras I and Farseev A
Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining., 1196-1199.  
27-02-2023
Relevant PublicationStyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG). vol. 00, 1-8.  
08-01-2023
Relevant PublicationArtistic neural style transfer using CycleGAN and FABEMD by adaptive information selection
Batziou E, Ioannidis K, Patras I, Vrochidis S and Kompatsiaris I
Pattern Recognition Letters, Elsevier vol. 165, 55-62.  
01-01-2023
Relevant PublicationLow-Light Image Enhancement Based on U-Net and Haar Wavelet Pooling
Batziou E, Ioannidis K, Patras I, Vrochidis S and Kompatsiaris I
Lecture Notes in Computer Science. vol. 13834, 510-522.  
01-01-2023
Relevant PublicationPANDA: UNSUPERVISED LEARNING OF PARTS AND APPEARANCES IN THE FEATURE MAPS OF GANS
Oldfield J, Tzelepis C, Panagakis Y, Nicolaou MA and Patras I
11th International Conference on Learning Representations, ICLR 2023. 
01-01-2023
Relevant PublicationA Simple Baseline for Knowledge-Based Visual Question Answering
Xenos A, Stafylakis T, Patras I and Tzimiropoulos G
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing., 14871-14877.  
01-01-2023
Relevant PublicationPrompting Visual-Language Models for Dynamic Facial Expression Recognition.
Zhao Z and Patras I
CoRR. vol. abs/2308.13382 
01-01-2023
bullet iconParts of Speech-Grounded Subspaces in Vision-Language Models
Oldfield J, Tzelepis C, Panagakis Y, Nicolaou MA and Patras I
Advances in Neural Information Processing Systems. vol. 36 
01-01-2023
Relevant PublicationParts of Speech-Grounded Subspaces in Vision-Language Models.
Oldfield J, Tzelepis C, Panagakis Y, Nicolaou MA and Patras I
CoRR. vol. abs/2305.14053 
01-01-2023
Relevant PublicationA Simple Baseline for Knowledge-Based Visual Question Answering.
Xenos A, Stafylakis T, Patras I and Tzimiropoulos G
EMNLP., 14871-14877. Editors: Bouamor H, Pino J and Bali K. 
01-01-2023
Relevant PublicationSimDETR: Simplifying self-supervised pretraining for DETR.
Metaxas IM, Bulat A, Patras I, Martínez B and Tzimiropoulos G
Corr vol. abs/2307.15697 
01-01-2023
Relevant PublicationMachine Learning Approaches for Fine-Grained Symptom Estimation in Schizophrenia: A Comprehensive Review.
Foteinopoulou NM and Patras I
Corr vol. abs/2310.16677 
01-01-2023
Relevant PublicationAttribute-Preserving Face Dataset Anonymization via Latent Code Optimization.
Barattin S, Tzelepis C, Patras I and Sebe N
CVPR., 8001-8010.  
01-01-2023
Relevant PublicationStyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment.
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
FG., 1-8.  
01-01-2023
Relevant PublicationSelf-Supervised Video Similarity Learning.
Kordopatis-Zilos G, Tolias G, Tzelepis C, Kompatsiaris I, Patras I and Papadopoulos S
CVPR Workshops., 4756-4766.  
01-01-2023
Relevant PublicationHyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces.
Bounareli S, Tzelepis C, Argyriou V, Patras I and Tzimiropoulos G
ICCV., 7115-7125.  
01-01-2023
Relevant PublicationPandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs.
Oldfield J, Tzelepis C, Panagakis Y, Nicolaou M and Patras I
ICLR. 
01-01-2023

2022

Relevant PublicationExplaining video summarization based on the focus of attention
Apostolidis E, Balaouras G, Mezaris V and Patras I
2022 IEEE International Symposium on Multimedia (ISM). vol. 00, 146-150.  
07-12-2022
Relevant PublicationAdaptive Soft Contrastive Learning
Feng C and Patras I
2022 26th International Conference on Pattern Recognition (ICPR). 
29-11-2022
Relevant PublicationLearning from Label Relationships in Human Affect
Foteinopoulou N and Patras I
Proceedings of the 30th ACM International Conference on Multimedia (MM '22) Lisboa, Portugal 10 Oct 2022 - 14 Oct 2022. 
10-10-2022
Relevant PublicationVideo Summarization in the Deep Learning Era
Patras I
Proceedings of the 1st Workshop on User-centric Narrative Summarization of Long Videos., 1-1.  
10-10-2022
Relevant PublicationAdaptive Soft Contrastive Learning
Feng C and Patras I
2022 26th International Conference on Pattern Recognition (ICPR). vol. 00, 2721-2727.  
25-08-2022
Relevant PublicationDnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval
Kordopatis-Zilos G, Tzelepis C, Papadopoulos S, Kompatsiaris I and Patras I
International Journal of Computer Vision, Springer Nature vol. 130 (10), 2385-2407.  
05-08-2022
Relevant PublicationSummarizing Videos using Concentrated Attention and Considering the Uniqueness and Diversity of the Video Frames
Apostolidis E, Balaouras G, Mezaris V and Patras I
Proceedings of the 2022 International Conference on Multimedia Retrieval., 407-415.  
27-06-2022
Relevant PublicationCovMix: Covariance Mixing Regularization for Motor Imagery Decoding
Zoumpourlis G and Patras I
2022 10th International Winter Conference on Brain-Computer Interface (BCI). vol. 00, 1-7.  
23-02-2022
Relevant PublicationSSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
Feng C, Tzimiropoulos G and Patras I
BMVC 2022 - 33rd British Machine Vision Conference Proceedings. 
01-01-2022
Relevant PublicationContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentences.
Tzelepis C, Oldfield J, Tzimiropoulos G and Patras I
Corr vol. abs/2206.02104 
01-01-2022
Relevant PublicationVideo Summarization in the Deep Learning Era: Current Landscape and Future Directions.
Patras I
NarSUM@MM., 1-1. Editors: Kankanhalli MS, Liu J and Wong Y. 
01-01-2022
Relevant PublicationDnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval.
Kordopatis-Zilos G, Tzelepis C, Papadopoulos S, Kompatsiaris I and Patras I
Int. J. Comput. Vis. vol. 130, 2385-2407.  
01-01-2022
Relevant PublicationLearning from Label Relationships in Human Affect.
Foteinopoulou NM and Patras I
ACM Multimedia., 80-89. Editors: Magalhães J, Bimbo AD, Satoh S, Sebe N, Alameda-Pineda X, Jin Q, Oria V and Toni L. 
01-01-2022

2021

bullet iconCombining Global and Local Attention with Positional Encoding for Video Summarization
Apostolidis E, Balaouras G, Mezaris V and Patras I
2021 IEEE International Symposium on Multimedia (ISM). vol. 00, 226-234.  
01-12-2021
Relevant PublicationSSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
Feng C, Tzimiropoulos G and Patras I
 
22-11-2021
Relevant PublicationVideo Summarization Using Deep Neural Networks: A Survey
Apostolidis E, Adamantidou E, Metsai AI, Mezaris V and Patras I
Proceedings of The Ieee, Institute of Electrical and Electronics Engineers (Ieee) vol. 109 (11), 1838-1863.  
01-11-2021
Relevant PublicationWarpedGANSpace: Finding non-linear RBF paths in GAN latent space
Tzelepis C, Tzimiropoulos G and Patras I
2021 IEEE/CVF International Conference on Computer Vision (ICCV). vol. 00, 6373-6382.  
17-10-2021
bullet iconEstimating continuous affect with label uncertainty
Foteinopoulou NM, TZELEPIS C and Patras I
2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII) 28 Sep 2021 - 1 Oct 2021. 
01-10-2021
Relevant PublicationPairwise Ranking Network for Affect Recognition
Zoumpourlis G and Patras I
9th International Conference on Affective Computing and Intelligent Interaction (ACII 2021). 
01-09-2021
Relevant PublicationFew-Shot Action Localization without Knowing Boundaries
Xie T-T, Tzelepis C, Fu F and Patras I
Proceedings of the 2021 International Conference on Multimedia Retrieval., 339-348.  
24-08-2021
bullet iconCombining Adversarial and Reinforcement Learning for Video Thumbnail Selection
Apostolidis E, Adamantidou E, Mezaris V and Patras I
Proceedings of the 2021 International Conference on Multimedia Retrieval., 1-9.  
24-08-2021
bullet iconCycle-Consistent Adversarial Networks and Fast Adaptive Bi-dimensional Empirical Mode Decomposition for Style Transfer
Batziou E, Alvanitopoulos P, Ioannidis K, Patras I, Vrochidis S and Kompatsiaris I
2020 25th International Conference on Pattern Recognition (ICPR). vol. 00, 2360-2367.  
15-01-2021
bullet iconMultiMedia Modeling - 27th International Conference, MMM 2021, Prague, Czech Republic, June 22-24, 2021, Proceedings, Part I

MMM (1). vol. 12572 Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMultiMedia Modeling - 27th International Conference, MMM 2021, Prague, Czech Republic, June 22-24, 2021, Proceedings, Part II

MMM (2). vol. 12573 Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconThe MovieWall: A New Interface for Browsing Large Video Collections.
Nefkens M and Hürst W
MMM (2). vol. 12573, 170-182. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGraph-Based Indexing and Retrieval of Lifelog Data.
Nguyen M-D, Binh NT and Gurrin C
MMM (2). vol. 12573, 256-267. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconSOMHunter V2 at Video Browser Showdown 2021.
Veselý P, Mejzlík F and Lokoc J
MMM (2). vol. 12573, 461-466. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFine-Grained Generation for Zero-Shot Learning.
Sun W, Xu J and Yang G
MMM (1). vol. 12572, 580-591. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconKeystroke Dynamics as Part of Lifelogging.
Smeaton AF, Krishnamurthy NG and Suryanarayana AH
MMM (2). vol. 12573, 183-195. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconIVOS - The ITEC Interactive Video Object Search System at VBS2021.
Ressmann A and Schoeffmann K
MMM (2). vol. 12573, 479-483. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGroup Activity Recognition by Exploiting Position Distribution and Appearance Relation.
Pei D, Li A and Wang Y
MMM (1). vol. 12572, 123-135. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDANet: Deformable Alignment Network for Video Inpainting.
Lu X and Zhang J
MMM (1). vol. 12572, 430-442. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMulti-grained Fusion for Conditional Image Retrieval.
Liu Y and Lu Y
MMM (1). vol. 12572, 315-327. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGame Input with Delay - A Model of the Time Distribution for Selecting a Moving Target with a Mouse.
Liu S and Claypool M
MMM (1). vol. 12572, 506-518. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLess is More - diveXplore 5.0 at VBS 2021.
Leibetseder A and Schoeffmann K
MMM (2). vol. 12573, 455-460. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTowards the Development of a Trustworthy Chatbot for Mental Health Applications.
Kraus M, Seldschopf P and Minker W
MMM (2). vol. 12573, 354-366. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconImage Registration Improved by Generative Adversarial Networks.
Jiang S, Wang C and Huang C
MMM (2). vol. 12573, 26-35. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconSearch and Explore Strategies for Interactive Analysis of Real-Life Image Collections with Unknown and Unique Categories.
Gisolf F, Geradts ZJMH and Worring M
MMM (2). vol. 12573, 244-255. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMulti-task Deep Learning for No-Reference Screen Content Image Quality Assessment.
Gao R, Huang Z and Liu S
MMM (1). vol. 12572, 213-226. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconSpotifyGraph: Visualisation of User's Preferences in Music.
Gajdusek P and Peska L
MMM (2). vol. 12573, 379-384. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconOn Fusion of Learned and Designed Features for Video Data Analytics.
Dobranský M and Skopal T
MMM (2). vol. 12573, 268-280. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDeepFusion: Deep Ensembles for Domain Independent System Fusion.
Constantin MG, Stefan L-D and Ionescu B
MMM (1). vol. 12572, 240-252. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconThermal Face Recognition Based on Multi-scale Image Synthesis.
Chu W-T and Huang P-S
MMM (1). vol. 12572, 99-110. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconSpatial Gradient Guided Learning and Semantic Relation Transfer for Facial Landmark Detection.
Wang J, Li Y and Lu H
MMM (1). vol. 12572, 678-690. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGraph Structure Reasoning Network for Face Alignment and Reconstruction.
Wang X, Li X and Wu S
MMM (1). vol. 12572, 493-505. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFew-Shot Learning with Unlabeled Outlier Exposure.
Wang H, Lian J and Xiong S
MMM (1). vol. 12572, 340-351. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMobile eHealth Platform for Home Monitoring of Bipolar Disorder.
Codina-Filbà J, Escalera S, Escudero J, Antens C, Buch-Cardona P and Farrús M
MMM (2). vol. 12573, 330-341. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTwo-Stage Real-Time Multi-object Tracking with Candidate Selection.
Wang F, Luo L and Zhu E
MMM (2). vol. 12573, 49-61. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGaussian Mixture Model Based Semi-supervised Sparse Representation for Face Recognition.
Shan X and Wen Y
MMM (1). vol. 12572, 716-727. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGenerative Image Inpainting by Hybrid Contextual Attention Network.
Xiao Z and Li D
MMM (1). vol. 12572, 162-173. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFusion of Multimodal Sensor Data for Effective Human Action Recognition in the Service of Medical Platforms.
Giannakeris P, Tsanousa A, Mavropoulos T, Meditskos G, Ioannidis K, Vrochidis S and Kompatsiaris I
MMM (2). vol. 12573, 367-378. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTime-Dependent Body Gesture Representation for Video Emotion Recognition.
Wei J, Yang X and Dong Y
MMM (1). vol. 12572, 403-416. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDeep Centralized Cross-modal Retrieval.
Wen Z and Feng A
MMM (1). vol. 12572, 443-455. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconEEG Emotion Recognition Based on Channel Attention for E-Healthcare Applications.
Zhang X, Du T and Zhang Z
MMM (2). vol. 12573, 159-169. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMulti-granularity Recurrent Attention Graph Neural Network for Few-Shot Learning.
Zhang X, Zhang Y and Zhang Z
MMM (2). vol. 12573, 147-158. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMusiCoder: A Universal Music-Acoustic Encoder Based on Transformer.
Zhao Y and Guo J
MMM (1). vol. 12572, 417-429. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFine-Grained Image-Text Retrieval via Complementary Feature Learning.
Zheng M, Jia Y and Jiang H
MMM (1). vol. 12572, 592-604. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconInitialize with Mask: For More Efficient Federated Learning.
Zhu Z and Sun L
MMM (2). vol. 12573, 111-120. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLocating Visual Explanations for Video Question Answering.
Chen X, Liu R, Song X and Han Y
MMM (1). vol. 12572, 290-302. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconCrossed-Time Delay Neural Network for Speaker Recognition.
Chen L, Liang Y, Shi X, Zhou Y and Wu C
MMM (1). vol. 12572, 1-10. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDVRCNN: Dark Video Post-processing Method for VVC.
Feng D, Zhang Y, Zhu C, Zhang H and Song L
MMM (1). vol. 12572, 691-703. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconIVIST: Interactive Video Search Tool in VBS 2021.
Lee Y, Choi H, Park S and Ro YM
MMM (2). vol. 12573, 423-428. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLearning 3D-Craft Generation with Predictive Action Neural Network.
Liu Z-Y, Liu J-W, Zuo X and Li W
MMM (1). vol. 12572, 541-553. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconImproving Supervised Cross-modal Retrieval with Semantic Graph Embedding.
Feng C, Li D and Zheng J
MMM (1). vol. 12572, 187-199. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconUnsupervised Gaze: Exploration of Geometric Constraints for 3D Gaze Estimation.
Lu Y, Wang Y, Xin Y, Wu D and Lu G
MMM (2). vol. 12573, 121-133. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMNR-Air: An Economic and Dynamic Crowdsourcing Mechanism to Collect Personal Lifelog and Surrounding Environment Dataset. A Case Study in Ho Chi Minh City, Vietnam.
Nguyen D-H, Tan LTN, Nguyen M-T, Nguyen T-B and Dao M-S
MMM (2). vol. 12573, 206-217. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconRobust Multispectral Pedestrian Detection via Uncertainty-Aware Cross-Modal Learning.
Park S, Kim JU, Kim Y, Moon S-K and Ro YM
MMM (1). vol. 12572, 391-402. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconIlluminate Low-Light Image via Coarse-to-fine Multi-level Network.
Qiu Y, Chen J, Wang X and Jang K
MMM (1). vol. 12572, 253-264. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFast Optimal Transport Artistic Style Transfer.
Qiu T, Ni B, Liu Z and Chen X
MMM (1). vol. 12572, 37-49. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTowards Optimal Multirate Encoding for HTTP Adaptive Streaming.
Amirpour H, Çetinkaya E, Timmerer C and Ghanbari M
MMM (1). vol. 12572, 469-480. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconVideoGraph - Towards Using Knowledge Graphs for Interactive Video Retrieval.
Rossetto L, Baumgartner M, Ashena N, Ruosch F, Pernisch R, Heitz L and Bernstein A
MMM (2). vol. 12573, 417-422. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMedian-Pooling Grad-CAM: An Efficient Inference Level Visual Explanation for CNN Networks in Remote Sensing Image Classification.
Song W, Dai S, Huang D, Song J and Liotta A
MMM (2). vol. 12573, 134-146. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDiscriminative and Selective Pseudo-Labeling for Domain Adaptation.
Wang F, Ding Y, Liang H and Wen J
MMM (1). vol. 12572, 365-377. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconShot Boundary Detection Through Multi-stage Deep Convolution Neural Network.
Wang T, Feng N, Yu J, He Y, Hu Y and Chen Y-PP
MMM (1). vol. 12572, 456-468. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconStacked Sparse Autoencoder for Audio Object Coding.
Wu Y, Hu R, Wang X, Hu C and Li G
MMM (1). vol. 12572, 50-61. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconSQL-Like Interpretable Interactive Video Search.
Wu J, Nguyen PA, Ma Z and Ngo C-W
MMM (2). vol. 12573, 391-397. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFast Mode Decision Algorithm for Intra Encoding of the 3rd Generation Audio Video Coding Standard.
Wu S, Wang Z, Cai Y and Wang R
MMM (1). vol. 12572, 481-492. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconUnsupervised Temporal Attention Summarization Model for User Created Videos.
Hu M, Hu R, Wang X and Sheng R
MMM (1). vol. 12572, 519-530. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconUnsupervised Multi-shot Person Re-identification via Dynamic Bi-directional Normalized Sparse Representation.
Li X, Wang W, Li Q and Guo L
MMM (1). vol. 12572, 554-566. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFrame Aggregation and Multi-modal Fusion Framework for Video-Based Person Recognition.
Li F, Wang W, Liu Z, Wang H, Yan C and Wu B
MMM (1). vol. 12572, 75-86. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMM-Net: Learning Adaptive Meta-metric for Few-Shot Biometric Recognition.
Gu Q, Luo Z, Zhao W and Zhu Y
MMM (1). vol. 12572, 265-277. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconImplementation of a Random Forest Classifier to Examine Wildfire Predictive Modelling in Greece Using Diachronically Collected Fire Occurrence and Fire Mapping Data.
Apostolakis A, Girtsou S, Kontoes C, Papoutsis I and Tsoutsos M
MMM (2). vol. 12573, 318-329. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMultimodal Sensor Data Analysis for Detection of Risk Situations of Fragile People in @home Environments.
Yebda T, Benois-Pineau J, Pech M, Amieva H, Middleton L and Bergelt M
MMM (2). vol. 12573, 342-353. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTowards Explainable Interactive Multi-modal Video Retrieval with Vitrivr.
Heller S, Gasser R, Illi C, Pasquinelli M, Sauter L, Spiess F and Schuldt H
MMM (2). vol. 12573, 435-440. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconVideo Search with Sub-Image Keyword Transfer Using Existing Image Archives.
Hezel N, Schall K, Jung K and Barthel KU
MMM (2). vol. 12573, 484-489. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTropical Cyclones Tracking Based on Satellite Cloud Images: Database and Comprehensive Study.
Huang C, Chan S, Bai C, Ding W and Zhang J
MMM (2). vol. 12573, 13-25. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconVideo Search with Collage Queries.
Lokoc J, Bátoryová J, Smrz D and Dobranský M
MMM (2). vol. 12573, 429-434. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconTell as You Imagine: Sentence Imageability-Aware Image Captioning.
Umemura K, Kastner MA, Ide I, Kawanishi Y, Hirayama T, Doman K, Deguchi D and Murase H
MMM (2). vol. 12573, 62-73. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDeep Face Swapping via Cross-Identity Adversarial Training.
Yang S, Xue H, Ling J, Song L and Xie R
MMM (2). vol. 12573, 74-86. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDeep 3D Modeling of Human Bodies from Freehand Sketching.
Yang K, Lu J, Hu S and Chen X
MMM (2). vol. 12573, 36-48. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMulti-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization.
Zhang F, Li M, Zhai G and Liu Y
MMM (1). vol. 12572, 136-147. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconExquisitor at the Video Browser Showdown 2021: Relationships Between Semantic Classifiers.
Khan OS, Jónsson BÞ, Larsen MD, Poulsen LAS, Koelma DC, Rudinac S, Worring M and Zahálka J
MMM (2). vol. 12573, 410-416. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDense Attention-Guided Network for Boundary-Aware Salient Object Detection.
Zhang Z, Ma J, Xu P and Wang W
MMM (1). vol. 12572, 148-161. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconNoShot Video Browser at VBS2021.
Karisch C, Leibetseder A and Schoeffmann K
MMM (2). vol. 12573, 405-409. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconHTAD: A Home-Tasks Activities Dataset with Wrist-Accelerometer and Audio Features.
Garcia-Ceja E, Thambawita V, Hicks SA, Jha D, Jakobsen P, Hammer HL, Halvorsen P and Riegler MA
MMM (2). vol. 12573, 196-205. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLearning Multi-level Interaction Relations and Feature Representations for Group Activity Recognition.
Lu L, Lu Y and Wang S
MMM (1). vol. 12572, 617-628. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMulti-level Gate Feature Aggregation with Spatially Adaptive Batch-Instance Normalization for Semantic Image Synthesis.
Long J and Lu H
MMM (1). vol. 12572, 378-390. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconDeep Attributed Network Embedding with Community Information.
Xue L, Yao W, Xia Y and Li X
MMM (1). vol. 12572, 653-665. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLanguage Person Search with Pair-Based Weighting Loss.
Zhang P, Ouyang D, Jiang C and Shao J
MMM (1). vol. 12572, 227-239. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconGlobal Cognition and Local Perception Network for Blind Image Deblurring.
Zhang C, Zhang W, Chen F, Cheng Y and Gao S
MMM (1). vol. 12572, 303-314. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFine-Grained Video Deblurring with Event Camera.
Zhang L, Zhang H, Zhu C, Guo S, Chen J and Wang L
MMM (1). vol. 12572, 352-364. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconMSCANet: Adaptive Multi-scale Context Aggregation Network for Congested Crowd Counting.
Zhang Y, Zhao H, Zhou F, Zhang Q, Shi Y and Liang L
MMM (2). vol. 12573, 1-12. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconLearning from the Negativity: Deep Negative Correlation Meta-Learning for Adversarial Image Classification.
Zheng W, Yan L, Wang F-Y and Gou C
MMM (1). vol. 12572, 531-540. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconVERGE in VBS 2021.
Andreadis S, Moumtzidou A, Gkountakos K, Pantelidis N, Apostolidis K, Galanopoulos D, Gialampoukidis I, Vrochidis S, Mezaris V and Kompatsiaris I
MMM (2). vol. 12573, 398-404. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconKvasir-Instrument: Diagnostic and Therapeutic Tool Segmentation Dataset in Gastrointestinal Endoscopy.
Jha D, Ali S, Emanuelsen K, Hicks SA, Thambawita V, Garcia-Ceja E, Riegler MA, Lange TD, Schmidt PT, Johansen HD, Johansen D and Halvorsen P
MMM (2). vol. 12573, 218-229. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconFast Discrete Matrix Factorization Hashing for Large-Scale Cross-Modal Retrieval.
Zhao H, She X, Wang S and Ma K
MMM (1). vol. 12572, 24-36. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
bullet iconRes2-Unet: An Enhanced Network for Generalized Nuclear Segmentation in Pathological Images.
Zhao S, Li X, Chen Z, Liu C and Peng C
MMM (2). vol. 12573, 87-98. Editors: Lokoc J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I. 
01-01-2021
Relevant PublicationUncertainty Propagation in Convolutional Neural Networks: Technical Report.
Tzelepis C and Patras I
Corr vol. abs/2102.06064 
01-01-2021
Relevant PublicationPreface
Lokoč J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I
 
01-01-2021
Relevant PublicationRelationship-based Neural Baby Talk.
Fu F, Xie T, Patras I and Jalali S
Corr vol. abs/2103.04846 
01-01-2021
bullet iconTensor Component Analysis for Interpreting the Latent Space of GANs
Oldfield J, Georgopoulos M, Panagakis Y, Nicolaou MA and Patras I
32nd British Machine Vision Conference, BMVC 2021. 
01-01-2021
Relevant PublicationVideo Summarization Using Deep Neural Networks: A Survey.
Apostolidis E, Adamantidou E, Metsai AI, Mezaris V and Patras I
Proc. Ieee vol. 109, 1838-1863.  
01-01-2021
Relevant PublicationTensor Component Analysis for Interpreting the Latent Space of GANs.
Oldfield J, Georgopoulos M, Panagakis Y, Nicolaou MA and Patras I
BMVC., 222-222.  
01-01-2021
Relevant PublicationSchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis.
Bishay M, Palasek P, Priebe S and Patras I
Ieee Trans. Affect. Comput. vol. 12, 949-961.  
01-01-2021
Relevant PublicationS3: Supervised Self-supervised Learning under Label Noise.
Feng C, Tzimiropoulos G and Patras I
Corr vol. abs/2111.11288 
01-01-2021
Relevant PublicationWarpedGANSpace: Finding non-linear RBF paths in GAN latent space.
Tzelepis C, Tzimiropoulos G and Patras I
Corr vol. abs/2109.13357 
01-01-2021
Relevant PublicationFew-Shot Action Localization without Knowing Boundaries.
Xie T-T, Tzelepis C, Fu F and Patras I
ICMR., 339-348. Editors: Cheng W-H, Kankanhalli MS, Wang M, Chu W-T, Liu J and Worring M. 
01-01-2021

2020

Relevant PublicationAC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial Networks for Unsupervised Video Summarization
Apostolidis E, Adamantidou E, Metsai A, Mezaris V and Patras I
Ieee Transactions On Circuits and Systems For Video Technology, Institute of Electrical and Electronics Engineers 
16-11-2020
bullet iconPerformance over Random: A Robust Evaluation Protocol for Video Summarization Methods
Apostolidis E, Adamantidou E, Metsai AI, Mezaris V and Patras I
MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia., 1056-1064.  
12-10-2020
bullet iconPerformance over Random
Apostolidis E, Adamantidou E, Metsai AI, Mezaris V and Patras I
Proceedings of the 28th ACM International Conference on Multimedia., 1056-1064.  
12-10-2020
bullet iconITI-CERTH participation to TRECVID 2015
Markatopoulou F, Ioannidou A, Tzelepis C, Mironidis T, Galanopoulos D, Arestis-Chartampilas S, Pittaras N, Avgerinakis K, Gkalelis N, Moumtzidou A, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
2015 TREC Video Retrieval Evaluation, TRECVID 2015. 
01-01-2020
bullet iconITI-CERTH participation to TRECVID 2014
Gkalelis N, Markatopoulou F, Moumtzidou A, Galanopoulos D, Avgerinakis K, Pittaras N, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
2014 TREC Video Retrieval Evaluation, TRECVID 2014. 
01-01-2020
Relevant PublicationTemporal Action Localization with Variance-Aware Networks.
Xie T-T, Tzelepis C and Patras I
Corr vol. abs/2008.11254 
01-01-2020
Relevant PublicationBoundary Uncertainty in a Single-Stage Temporal Action Localization Network.
Xie T, Tzelepis C and Patras I
Corr vol. abs/2008.11170 
01-01-2020

2019

bullet iconUnsupervised Video Summarization via Attention-Driven Adversarial Learning
Apostolidis E, Adamantidou E, Metsai A, Mezaris V and Patras I
26th Int. Conf. on Multimedia Modeling (MMM2020) Daejeon, Korea 5 Jan 2020 - 8 Jan 2020. 
24-12-2019
bullet iconViSiL: Fine-grained Spatio-Temporal Video Similarity Learning
Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I
2019 IEEE/CVF International Conference on Computer Vision (ICCV). vol. 00, 6350-6359.  
02-11-2019
bullet iconViSiL: Fine-grained Spatio-Temporal Video Similarity Learning
Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I
International Conference on Computer Vision Seoul. Korea 27 Sep 2019 - 2 Nov 2019., 6351-6360.  
31-10-2019
bullet iconA Stepwise, Label-based Approach for Improving the Adversarial Training in Unsupervised Video Summarization
Apostolidis E, Metsai AI, Adamantidou E, Mezaris V and Patras I
the 1st International Workshop 21 Oct 2019. 
21-10-2019
Relevant PublicationVideo Fragmentation and Reverse Search on the Web
Apostolidis E, Apostolidis K, Patras I and Mezaris V
In Video Verification in The Fake News Era, Springer, Cham 53-90. Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. 
18-09-2019
Relevant PublicationFinding Semantically Related Videos in Closed Collections
MARKATOPOULOU F, Zampoglou M, Apostolidis E, Papadopoulos S, Mezaris V, Patras I and Kompatsiaris I
In Video Verification in The Fake News Era, Springer, Cham 127-159. Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. 
18-09-2019
Relevant PublicationDetecting Manipulations in Video
Mercier G, MARKATOPOULOU F, Cozien R, Zampoglou M, Apostolidis E, Metsai A, Papadopoulos S, Mezaris V, Patras I and Kompatsiaris I
In Video Verification in The Fake News Era, Springer, Cham 161-189. Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. 
18-09-2019
Relevant PublicationFinding Near-Duplicate Videos in Large-Scale Collections
Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I
In Video Verification in The Fake News Era, Springer 91-126. Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. 
18-09-2019
bullet iconTARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
Bishay M, Zoumpourlis G and Patras I
30th British Machine Vision Conference Cardiff, UK 9 Sep 2019 - 12 Sep 2019. 
09-09-2019
Relevant PublicationAlone versus In-a-group
Mou W, Gunes H and Patras I
Acm Transactions On Multimedia Computing Communications and Applications, Association For Computing Machinery (Acm) vol. 15 (2), 1-23.  
31-05-2019
bullet iconYour Fellows Matter: Affect Analysis across Subjects in Group Videos
Mou W, Gunes H and Patras I
2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019). vol. 00, 1-5.  
18-05-2019
Relevant PublicationRegistration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild
Jang Y, Gunes H and Patras I
Computer Vision and Image Understanding, Elsevier vol. 182, 17-29.  
01-05-2019
bullet iconCAN AUTOMATIC FACIAL EXPRESSION ANALYSIS BE USED FOR TREATMENT OUTCOME ESTIMATION IN SCHIZOPHRENIA?
BISHAY MAT, PATRAS I and PRIEBE S
IEEE International Conference on Acoustics, Speech and Signal Processing Brighton 12 May 2019 - 17 May 2019. 
17-04-2019
Relevant PublicationSchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis.
Bishay M, PALASEK P, PRIEBE S and Patras I
Ieee Transactions On Affective Computing 
26-03-2019
Relevant PublicationFIVR: Fine-grained Incident Video Retrieval.
Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I
Ieee Transactions On Multimedia, Institute of Electrical and Electronics Engineers vol. 21 (10), 2638-2652.  
18-03-2019
bullet iconExploring Feature Representation and Training Strategies in Temporal Action Localization
Xie T, Yang X, Zhang T, Xu C and Patras I
2019 IEEE International Conference on Image Processing (ICIP). vol. 00, 1605-1609.  
25-01-2019
bullet iconDetecting Tampered Videos with Multimedia Forensics and Deep Learning
Zampoglou M, Markatopoulou F, Mercier G, Touska D, Apostolidis E, Papadopoulos S, Cozien R, Patras I, Mezaris V and Kompatsiaris I
25th International Conference on MultiMedia Modeling Thessaloniki, Greece 8 Jan 2019 - 11 Jan 2019. vol. 11295 LNCS, 374-386.  
10-01-2019
bullet iconMultimodal Video Annotation for Retrieval and Discovery of Newsworthy Video in a News Verification Scenario
Nixon L, Apostolidis E, Markatopoulou F, Patras I and Mezaris V
25th International Conference on MultiMedia Modeling Thessaloniki, Greece 8 Jan 2019 - 11 Jan 2019. vol. 11295 LNCS, 143-155.  
09-01-2019
bullet iconLikeNet: A Siamese motion estimation network trained in an unsupervised way
Ahmadi A, Marras I and Patras I
British Machine Vision Conference 2018, BMVC 2018. 
01-01-2019
Relevant PublicationDeep Mixture of MRFs for Human Pose Estimation
Marras I, Palasek P and Patras I
Lecture Notes in Computer Science. vol. 11363, 717-733.  
01-01-2019
Relevant PublicationFIVR: Fine-Grained Incident Video Retrieval.
Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I
Ieee Trans. Multim. vol. 21, 2638-2652.  
01-01-2019
Relevant PublicationAlone versus In-a-group: A Multi-modal Framework for Automatic Affect Recognition.
Mou W, Gunes H and Patras I
Acm Trans. Multim. Comput. Commun. Appl. vol. 15, 47:1-47:1.  
01-01-2019
Relevant PublicationUniversal Foreground Segmentation Based on Deep Feature Fusion Network for Multi-Scene Videos
Tao Y, Ling Z and Patras I
Ieee Access, Institute of Electrical and Electronics Engineers (Ieee) vol. 7, 158326-158337.  
01-01-2019
Relevant PublicationExploring Feature Representation and Training strategies in Temporal Action Localization.
Xie T, Yang X, Zhang T, Xu C and Patras I
Corr vol. abs/1905.10608 
01-01-2019
Relevant PublicationRegistration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild.
Jang Y, Gunes H and Patras I
Corr vol. abs/1902.04042 
01-01-2019
Relevant PublicationTARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition.
Bishay M, Zoumpourlis G and Patras I
BMVC., 154-154.  
01-01-2019
Relevant PublicationConcept-Based and Event-Based Video Search in Large Video Collections
Markatopoulou F, Galanopoulos D, Tzelepis C, Mezaris V and Patras I
In Big Data Analytics For Large-Scale Multimedia Search 31-60.  
01-01-2019
Relevant PublicationYour Fellows Matter: Affect Analysis across Subjects in Group Videos.
Mou W, Gunes H and Patras I
FG., 1-5.  
01-01-2019

2018

bullet iconVERGE in VBS 2019
Andreadis S, Moumtzidou A, Galanopoulos D, Markatopoulou F, Apostolidis K, Mavropoulos T, Gialampoukidis I, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 11296, 602-608.  
11-12-2018
Relevant PublicationAMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups
Miranda Correa JA, Abadi MK, Sebe N and Patras I
Ieee Transactions On Affective Computing 
30-11-2018
bullet iconAMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups.
Correa JAM, Abadi MK, Sebe N and Patras I
Ieee Transactions On Affective Computing, Institute of Electrical and Electronics Engineers vol. 12, 479-493.  
30-11-2018
bullet iconA deep generic to specific recognition model for group membership analysis using non-verbal cues
Mou W, Tzelepis C, Mezaris V, Gunes H and Patras I
Image and Vision Computing 
03-10-2018
bullet iconImplicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation
Markatopoulou F, Mezaris V and Patras I
Ieee Transactions On Circuits and Systems For Video Technology 
16-06-2018
bullet iconA Model of Visual Search in the Presence of Age-Related Macular Degeneration
Vasilyev A, Hansard M, Mareschal I and Patras I
Proceedings of the AVA Christmas meeting. vol. 47 (5), 573-573.  
01-05-2018
bullet iconA Multi-Task Cascaded Network for Prediction of Affect, Personality, Mood and Social Context Using EEG Signals
Miranda-Correa JA and Patras I
2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)., 373-380.  
01-05-2018
bullet iconVERGE in VBS 2018
Moumtzidou A, Andreadis S, Markatopoulou F, Galanopoulos D, Gialampoukidis I, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 10705, 444-450.  
01-01-2018
bullet iconSemi-supervised Fisher vector network.
Palasek P and Patras I
Corr vol. abs/1801.04438 
01-01-2018
bullet iconVisual and audio analysis of movies video for emotion detection @ Emotional Impact of Movies task MediaEval 2018
Batziou E, Michail E, Avgerinakis K, Vrochidis S, Patras I and Kompatsiaris I
CEUR Workshop Proceedings. vol. 2283 
01-01-2018
bullet iconMultimedia Processing Essentials
Apostolidis K, Markatopoulou F, Tzelepis C, Mezaris V and Patras I
In Personal Multimedia Preservation, Springer Nature 47-98.  
01-01-2018
Relevant PublicationLinear Maximum Margin Classifier for Learning from Uncertain Data.
Tzelepis C, Mezaris V and Patras I
Ieee Trans. Pattern Anal. Mach. Intell. vol. 40, 2948-2962.  
01-01-2018

2017

Relevant PublicationDeep globally constrained MRFs for Human Pose Estimation
MARRAS I, PALASEK P and PATRAS I
IEEE International Conference on Computer Vision (ICCV) Venice, Italy 22 Oct 2017 - 29 Oct 2017. 
25-12-2017
Relevant PublicationLinear Maximum Margin Classifier for Learning from Uncertain Data
TZELEPIS C, PATRAS and MEZARIS V
Ieee Transactions On Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers 
10-11-2017
bullet iconNear-Duplicate Video Retrieval with Deep Metric Learning
KORDOPATIS-ZILOS G, Papadopoulos S, PATRAS I and Kompatsiaris I
Web-scale Vision and Social Media (VSM), ICCV 2017. 
23-10-2017
Relevant PublicationSmileNet: Registration-Free Smiling Face Detection in the Wild
Jang Y, Gunes H and Patras I
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)., 1581-1589.  
01-10-2017
bullet iconBackground Modelling Based on Generative Unet
Tao Y, Palasek P, Ling Z and Parras I
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)., 1-6.  
01-08-2017
Relevant PublicationDiscriminative convolutional Fisher vector network for action recognition
Palasek P and Patras I
 
19-07-2017
bullet iconFusing Multilabel Deep Networks for Facial Action Unit Detection
Bishay M and Patras I
Automatic Face & Gesture Recognition (FG 2017)., 681-688.  
28-06-2017
Relevant PublicationQuery and Keyframe Representations for Ad-hoc Video Search
Markatopoulou F, Galanopoulos D, Mezaris V and Patras I
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval., 407-411.  
06-06-2017
bullet iconVideoAnalysis4ALL
Collyda C, Apostolidis E, Pournaras A, Markatopoulou F, Mezaris V and Patras I
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval., 470-474.  
06-06-2017
Relevant PublicationConcept Language Models and Event-based Concept Number Selection for Zero-example Event Detection
Galanopoulos D, Markatopoulou F, Mezaris V and Patras I
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval., 397-401.  
06-06-2017
bullet iconDeep Refinement Convolutional Networks for Human Pose Estimation
Marras I, Palasek P and Patras I
2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)., 446-453.  
01-05-2017
bullet iconGeneric to Specific Recognition Models for Membership Analysis in Group Videos
Mou W, Tzelepis C, Mezaris V, Gunes H and Patras I
2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)., 512-517.  
01-05-2017
Relevant PublicationNear-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
KORDOPATIS-ZILOS G, Papadopoulos S, Patras I and Kompatsiaris Y
International Conference on Multimedia Modeling. vol. 10132 LNCS, 251-263.  
01-01-2017
bullet iconITI-CERTH participation in TRECVID 2017
Markatopoulou F, Moumtzidou A, Galanopoulos D, Avgerinakis K, Andreadis S, Gialampoukidis I, Tachos S, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
2017 TREC Video Retrieval Evaluation, TRECVID 2017. 
01-01-2017

2016

Relevant PublicationComparison of Fine-Tuning and Extension Strategies for Deep Convolutional Neural Networks
Pittaras N, Markatopoulou F, Mezaris V and Patras I
Lecture Notes in Computer Science. vol. 10132, 102-114.  
31-12-2016
bullet iconVERGE in VBS 2017
Moumtzidou A, Mironidis T, Markatopoulou F, Andreadis S, Gialampoukidis I, Galanopoulos D, Ioannidou A, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 10133, 486-492.  
31-12-2016
bullet iconAutomatic Recognition of Emotions and Membership in Group Videos
Mou W, Gunes H and Patras I
2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)., 1478-1486.  
16-12-2016
bullet iconAlone versus In-a-group
Mou W, Gunes H and Patras I
Proceedings of the 24th ACM international conference on Multimedia., 521-525.  
01-10-2016
Relevant PublicationDeep Multi-task Learning with Label Correlation Constraint for Video Concept Detection
Markatopoulou F, Mezaris V and Patras I
Proceedings of the 24th ACM international conference on Multimedia., 501-505.  
01-10-2016
Relevant PublicationUNSUPERVISED CONVOLUTIONAL NEURAL NETWORKS FOR MOTION ESTIMATION
AHMADI A and Patras I
Image Processing (ICIP), 2016 IEEE International Conference on Phoenix, Arizona, USA 25 Sep 2016 - 28 Sep 2016. 
19-08-2016
bullet iconAction recognition using saliency learned from recorded human gaze
Stefic D and Patras I
Image and Vision Computing, Elsevier vol. 52, 195-205.  
01-08-2016
bullet iconAction Recognition Using Convolutional Restricted Boltzmann Machines
Palasek P and Patras I
Proceedings of the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction., 3-8.  
06-06-2016
bullet iconSpecial Issue on Individual and Group Activities in Video Event Analysis
Wang L, Patras I, Zhang J, Mori G and Davis L
Computer Vision and Image Understanding, Elsevier vol. 144, 1-2.  
01-03-2016
bullet iconGaze movement-driven random forests for query clustering in automatic video annotation
Vrochidis S, Patras I and Kompatsiaris I
Multimedia Tools and Applications, Springer Nature vol. 76 (2), 2861-2889.  
22-01-2016
bullet iconVideo Event Detection Using Kernel Support Vector Machine with Isotropic Gaussian Sample Uncertainty (KSVM-iGSU)
Tzelepis C, Mezaris V and Patras I
Lecture Notes in Computer Science. vol. 9516, 3-15.  
01-01-2016
bullet iconOrdering of Visual Descriptors in a Classifier Cascade Towards Improved Video Concept Detection
Markatopoulou F, Mezaris V and Patras I
Lecture Notes in Computer Science. vol. 9516, 874-885.  
01-01-2016
bullet iconVERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
Moumtzidou A, Mironidis T, Apostolidis E, Markatopoulou F, Ioannidou A, Gialampoukidis I, Avgerinakis K, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 9517, 394-399.  
01-01-2016
bullet iconUnsupervised Convolutional Neural Networks for Motion Estimation
Ahmadi A and Patras I
2016 IEEE International Conference on Image Processing (ICIP)., 1629-1633.  
01-01-2016
bullet iconOnline Multi-Task Learning for Semantic Concept Detection in Video
Markatopoulou F, Mezaris V and Patras I
2016 IEEE International Conference on Image Processing (ICIP)., 186-190.  
01-01-2016
bullet iconVideo Aesthetic Quality Assessment Using Kernel Support Vector Machine with Isotropic Gaussian Sample Uncertainty (KSVM-IGSU)
Tzelepis C, Mavridaki E, Mezaris V and Patras I
2016 IEEE International Conference on Image Processing (ICIP)., 2410-2414.  
01-01-2016
bullet iconMinimal Filtered Channel Features for Pedestrian Detection
Kuranuki Y and Patras I
2016 23rd International Conference on Pattern Recognition (ICPR)., 681-686.  
01-01-2016
bullet iconLearning to detect video events from zero or very few video examples.
Tzelepis C, Galanopoulos D, Mezaris V and Patras I
Image Vis. Comput. vol. 53, 35-44.  
01-01-2016
bullet iconITI-CERTH in TRECVID 2016 Ad-hoc video search (AVS)
Markatopoulou F, Galanopoulos D, Patras I and Mezaris V
2016 TREC Video Retrieval Evaluation, TRECVID 2016. 
01-01-2016
bullet iconITI-CERTH participation in TRECVID 2016
Markatopoulou F, Moumtzidou A, Galanopoulos D, Mironidis T, Kaltsa V, Ioannidou A, Symeonidis S, Avgerinakis K, Andreadis S, Gialampoukidis I, Vrochidis S, Briassouli A, Mezaris V, Kompatsiaris I and Patras I
2016 TREC Video Retrieval Evaluation, TRECVID 2016. 
01-01-2016
bullet iconMultimodal Sensing in Affective Gaming
Kotsia I, Zafeiriou S, Goudelis G, Patras I and Karpouzis K
In Emotion in Games, Springer Nature 59-84.  
01-01-2016

2015

bullet iconLearning to detect video events from zero or very few video examples
Tzelepis C, Galanopoulos D, Mezaris V and Patras I
Image and Vision Computing vol. 53, 35-44.  
09-10-2015
bullet iconDECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses
Abadi MK, Subramanian R, Kia SM, Avesani P, Patras I and Sebe N
Ieee Transactions On Affective Computing, Institute of Electrical and Electronics Engineers (Ieee) vol. 6 (3), 209-222.  
01-09-2015
bullet iconConcept Detection in Multimedia Web Resources about Home Made Explosives
Kalpakis G, Tsikrika¹ T, Markatopoulou F, Pittaras N, Vrochidis S, Mezaris V, Parras I and Kompatsiaris I
2015 10th International Conference on Availability, Reliability and Security., 632-641.  
01-08-2015
bullet iconLocal Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video
Markatopoulou F, Mezaris V, Pittaras N and Patras I
Ieee Transactions On Emerging Topics in Computing, Institute of Electrical and Electronics Engineers (Ieee) vol. 3 (2), 193-204.  
04-06-2015
bullet iconCascade of forests for face alignment
Yang H, Zou C and Patras I
Iet Computer Vision, Institution of Engineering and Technology (Iet) vol. 9 (3), 321-330.  
01-06-2015
bullet iconA Flexible Calibration Method of Multiple Kinects for 3D Human Reconstruction
Palasek P, Yang H, Xu Z, Hajimirza N, Izquierdo E and Patras I
2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)., 1-4.  
01-06-2015
bullet iconRandom Subspace Supervised Descent Method for Regression Problems in Computer Vision
Yang H, Jia X, Patras I and Chan K-P
Ieee Signal Processing Letters, Institute of Electrical and Electronics Engineers (Ieee) vol. 22 (10), 1816-1820.  
01-06-2015
bullet iconMirror, Mirror on the Wall, Tell me, is the Error Small?
Yang H and Patras I
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)., 4685-4693.  
01-06-2015
bullet iconInference of Personality Traits and Affect Schedule by Analysis of Spontaneous Reactions to Affective Videos
Abadi MK, Correa JAM, Wache J, Yang H, Patras I and Sebe N
2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)., 1-8.  
01-05-2015
bullet iconRobust Face Alignment Under Occlusion via Regional Predictive Power Estimation
Yang H, He X, Jia X and Patras I
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers (Ieee) vol. 24 (8), 2393-2403.  
10-04-2015
bullet iconPrivileged Information-Based Conditional Structured Output Regression Forest for Facial Point Detection
Yang H and Patras I
Ieee Transactions On Circuits and Systems For Video Technology, Institute of Electrical and Electronics Engineers (Ieee) vol. 25 (9), 1507-1520.  
09-01-2015
bullet iconFace Alignment Assisted by Head Pose Estimation
Yang H, Mou W, Zhang Y, Patras I, Gunes H and Robinson P
, British Machine Vision Association and Society For Pattern Recognition, 130.1-130.13.  
01-01-2015
bullet iconVERGE: A Multimodal Interactive Video Search Engine
Moumtzidou A, Avgerinakis K, Apostolidis E, Markatopoulou F, Apostolidis K, Mironidis T, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 8936, 249-254.  
01-01-2015
bullet iconA Study on the Use of a Binary Local Descriptor and Color Extensions of Local Descriptors for Video Concept Detection
Markatopoulou F, Pittaras N, Papadopoulou O, Mezaris V and Patras I
Lecture Notes in Computer Science. vol. 8935, 282-293.  
01-01-2015
bullet iconMirror, mirror on the wall, tell me, is the error small?
Yang H and Patras I
Corr vol. abs/1501.05152 
01-01-2015
bullet iconCascade of Classifiers Based on Binary, Non-Binary and Deep Convolutional Network Descriptors for Video Concept Detection
Markatopoulou F, Mezaris V and Patras I
2015 IEEE International Conference on Image Processing (ICIP)., 1786-1790.  
01-01-2015
bullet iconIdentifying Valence and Arousal Levels via Connectivity between EEG Channels
Chen M, Han J, Guo L, Wang J and Patras I
2015 International Conference on Affective Computing and Intelligent Interaction (ACII)., 63-69.  
01-01-2015
bullet iconFace Alignment Assisted by Head Pose Estimation.
Yang H, Mou W, Zhang Y, Patras I, Gunes H and Robinson P
BMVC., 130.1-130.1. Editors: Xie X, Jones MW and Tam GKL. 
01-01-2015
bullet iconFace Pose Analysis
Patras I
In Encyclopedia of Biometrics, Springer Nature 462-467.  
01-01-2015
bullet iconThe effect of limiting the right of appeal on the quality of the public procurement management system: Case study of Romania
Patras MV, BǍnacu CS, Popescu AM and Patraş I
Proceedings of the 26th International Business Information Management Association Conference - Innovation Management and Sustainable Economic Competitive Advantage: From Regional Development to Global Growth, IBIMA 2015., 521-530.  
01-01-2015
bullet iconInference of Personality Traits and Affect Schedule by Analysis of Spontaneous Reactions to Affective Videos
Abadi MK, Correa JAM, Wache J, Yang H, Patras I, Sebe N and IEEE
2015 11TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOPS ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG), VOL. 3. 
01-01-2015
bullet iconITI-CERTH participation to TRECVID 2015
Markatopoulou F, Loannidou A, Tzelepis C, Mironidis T, Galanopoulos D, Arestis-Chartampilas S, Ras NP, Avgerinakis K, Gkalelis N, Moumtzidou A, Vrochidis S, Mezaris V, Kompatsiaris L and Patras L
2015 TREC Video Retrieval Evaluation, TRECVID 2015. 
01-01-2015
bullet iconFace Alignment
Gu L and Kanade T
In Encyclopedia of Biometrics, Springer Nature 435-439.  
01-01-2015

2014

bullet iconFine-Tuning Regression Forests Votes for Object Alignment in the Wild
Yang H and Patras I
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers (Ieee) vol. 24 (2), 619-631.  
18-12-2014
bullet iconMultimodal random forest based tensor regression
Kaymak S and Patras I
Iet Computer Vision, Institution of Engineering and Technology (Iet) vol. 8 (6), 650-657.  
01-12-2014
bullet iconLearning Visual Saliency Using Topographic Independent Component Analysis
Stefic D and Patras I
2014 IEEE International Conference on Image Processing (ICIP)., 1130-1134.  
01-10-2014
bullet iconNon-Invasive Player Experience Estimation from Body Motion and Game Context
Burelli P, Triantafyllidis G and Patras I
2014 IEEE Conference on Computational Intelligence and Games., 1-7.  
01-08-2014
bullet iconLearning visual saliency using topographic independent component analysis
Stefic D and Patras I
2014 IEEE International Conference on Image Processing, ICIP 2014., 1130-1134.  
28-01-2014
bullet iconITI-CERTH participation to TRECVID 2014
Gkalelis N, Markatopoulou F, Moumtzidou A, Galanopoulos D, Avgerinakis K, Pittaras N, Vrochidis S, Mezaris V, Kompatsiaris I and Patras I
2014 TREC Video Retrieval Evaluation, TRECVID 2014. 
01-01-2014
bullet iconFace sketch landmarks localization in the wild
Yang H, Zou C and Patras I
Ieee Signal Processing Letters vol. 21 (11), 1321-1325.  
01-01-2014
bullet iconStructured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning
Jia X, Yang H, Chan K-P and Patras I
Proceedings of the British Machine Vision Conference 2014., 85.1-85.13.  
01-01-2014

2013

bullet iconSieving Regression Forest Votes for Facial Feature Detection in the Wild
Yang H and Patras I
, Institute of Electrical and Electronics Engineers (Ieee), 1936-1943.  
01-12-2013
bullet iconSupervised Dictionary Learning for Action Localization
G VKB and Patras I
2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)., 1-8.  
01-04-2013
bullet iconFusion of facial expressions and EEG for implicit affective tagging
Koelstra S and Patras I
Image and Vision Computing vol. 31 (2), 164-174.  
01-01-2013
bullet iconPrivileged information-based Conditional Regression Forests for Facial Feature Detection
Yang H and Patras I
10th IEEE International Conference on Automatic Face and Gesture Recognition. 
01-01-2013
bullet iconExploiting Depth and Intensity Information for Head Pose Estimation with Random Forests and Tensor Models
Kaymak S and Patras I
Lecture Notes in Computer Science. vol. 7729, 160-170.  
01-01-2013
bullet iconCoupled Gaussian Processes for Pose-Invariant Facial Expression Recognition
Rudovic O, Pantic M and Patras IY
Ieee Transactions On Pattern Analysis and Machine Intelligence vol. 35 (6), 1357-1369.  
01-01-2013
bullet iconHigh order pLSA for indexing tagged images
Nikolopoulos S, Zafeiriou S, Patras I and Kompatsiaris I
Signal Processing vol. 93 (8), 2212-2228.  
01-01-2013
bullet iconExploring the Similarities of Neighboring Spatiotemporal Points for Action Pair Matching
Kotsia I and Patras I
Lecture Notes in Computer Science. vol. 7726, 624-635.  
01-01-2013
bullet iconSemi-Supervised Visual Recognition With Constrained Graph Regularized Non Negative Matrix Factorization
Guo W, Hu W, Boulgouris NV and Patras I
2013 IEEE International Conference on Image Processing., 2743-2747.  
01-01-2013

2012

Relevant PublicationHigher rank Support Tensor Machines for visual recognition
Kotsia I, Guo W and Patras I
Pattern Recognition, Elsevier vol. 45 (12), 4192-4203.  
01-12-2012
bullet iconNonlinear Independent Component Analysis for EEG-Based Brain-Computer Interface Systems
Oveisi F, Oveisi S, Efranian A and Patras I
In Independent Component Analysis For Audio and Biosignal Applications, Intechopen 
10-10-2012
bullet iconLearning Codebook Weights for Action Detection
G VKB and Patras I
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. vol. 1, 27-32.  
01-06-2012
bullet iconEXPLOITING GAZE MOVEMENTS FOR AUTOMATIC VIDEO ANNOTATION
Vrochidis S, Patras I and Kompatsiaris I
2012 13th International Workshop on Image Analysis for Multimedia Interactive Services. vol. 1, 1-4.  
01-05-2012
bullet iconAFFECTIVE GAMING: BEYOND USING SENSORS
Kotsia I, Patras I and Fotopoulos S
2012 5th International Symposium on Communications, Control and Signal Processing. vol. 1, 1-4.  
01-05-2012
Relevant PublicationTensor learning for regression.
Guo W, Kotsia I and Patras I
Ieee Trans Image Process vol. 21 (2), 816-827.  
01-02-2012
Relevant PublicationMax-margin Non-negative Matrix Factorization
Kumar BGV, Kotsia I and Patras I
Image and Vision Computing vol. 30 (4-5), 279-291.  
01-01-2012
Relevant PublicationTree-Structured Feature Extraction Using Mutual Information
Oveisi F, Oveisi S, Efranian A and Patras I
Ieee Transactions On Neural Networks and Learning Systems vol. 23 (1), 127-137.  
01-01-2012
bullet iconLeveraging social media for scalable object detection
Chatzilari E, Nikolopoulos S, Patras I and Kompatsiaris I
Pattern Recognition vol. 45 (8), 2962-2979.  
01-01-2012
bullet iconFace Parts Localization Using Structured-output Regression Forests
Yang H and Patras I
ACCV 2012. 
01-01-2012
bullet iconA Simple and Effective Extrinsic Calibration Method of a Camera and a Single Line Scanning Lidar
Yang H, Liu X and Patras I
ICPR 2012. 
01-01-2012
bullet iconCoupled 3D Tracking and Pose Optimization of Rigid Objects Using Particle Filter
Yang H, Zhang Y, Liu X and Patras I
ICPR 2012. 
01-01-2012
bullet iconSUPPORT TENSOR ACTION SPOTTING
Kotsia I and Patras I
2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)., 1397-1400.  
01-01-2012
bullet iconDEAP: A Database for Emotion Analysis Using Physiological Signals
Koelstra S, Muhl C, Soleymani M, Lee J-S, Yazdani A, Ebrahimi T, Pun T, Nijholt A and Patras IY
Ieee Transactions On Affective Computing vol. 3 (1), 18-31.  
01-01-2012
bullet iconImage Interpretation by Combining Ontologies and Bayesian Networks
Nikolopoulos S, Papadopoulos GT, Kompatsiaris I and Patras I
Lecture Notes in Computer Science. vol. 7297, 307-314.  
01-01-2012
bullet iconHigher Rank Support Tensor Machines
Kotsia I, Guo W and Patras I
Lecture Notes in Computer Science. vol. 7432, 31-40.  
01-01-2012

2011

bullet iconEvidence-driven image interpretation by combining implicit and explicit knowledge in a Bayesian network.
Nikolopoulos S, Papadopoulos GT, Kompatsiaris I and Patras I
Ieee Trans Syst Man Cybern B Cybern vol. 41 (5), 1366-1381.  
01-10-2011
bullet iconAn eye-tracking-based approach to facilitate interactive video search
Vrochidis S, Patras I and Kompatsiaris I
Proceedings of the 1st ACM International Conference on Multimedia Retrieval., 1-8.  
18-04-2011
Relevant PublicationSpatiotemporal localization and categorization of human actions in unsegmented image sequences.
Oikonomopoulos A, Patras I and Pantic M
Ieee Transactions On Image Processing vol. 20 (4), 1126-1140.  
01-04-2011
bullet iconContinuous Emotion Detection in Response to Music Videos
Soleymani M, Koelstra S, Patras I and Pun T
Face and Gesture 2011. vol. 1, 803-808.  
01-03-2011
Relevant PublicationSupport Tucker Machines
Kotsia I and Patras I
2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)., 633-640.  
01-01-2011
bullet iconUtilizing Implicit User Feedback to Improve Interactive Video Retrieval
Vrochidis S, Kompatsiaris I and Patras I
Advances in Multimedia, Hindawi vol. 2011 (1), 1-18.  
01-01-2011
bullet iconEnhancing Computer Vision Using the Collective Intelligence of Social Media
Chatzilari E, Nikolopoulos S, Patras I and Kompatsiaris I
In New Directions in Web Data Management 1, Springer Nature 235-271.  
01-01-2011
bullet iconMax-Margin Semi-NMF
Kumar VBG, Patras I and Kotsia I
Procedings of the British Machine Vision Conference 2011., 129.1-129.11.  
01-01-2011
bullet iconCombining Multi-modal Features for Social Media Analysis
Nikolopoulos S, Giannakidou E, Kompatsiaris I, Patras I and Vakali A
In Social Media Modeling and Computing, Springer Nature 71-96.  
01-01-2011
bullet iconITI-CERTH participation to TRECVID 2011
Moumtzidou A, Sidiropoulos P, Vrochidis S, Gkalelis N, Nikolopoulos S, Mezaris V, Kompatsiaris I and Patras I
2011 TREC Video Retrieval Evaluation Notebook Papers. 
01-01-2011
bullet iconHigher order Support tensor regression for head pose estimation
Guo W, Kotsia I and Patras I
International Workshop on Image Analysis for Multimedia Interactive Services. 
01-01-2011

2010

Relevant PublicationA Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models
Koelstra S, Pantic M and Patras I
Ieee Transactions On Pattern Analysis and Machine Intelligence vol. 32 (11), 1940-1954.  
01-11-2010
bullet iconDiscriminative space-time voting for joint recognition and localization of actions.
Oikonomopoulos A, Patras I and Pantic M
Proceedings of the 2nd international workshop on Social signal processing., 11-16.  
29-10-2010
bullet iconAspect coherence for graph-based semantic image labelling
Passino G, Patras I and Izquierdo E
Computer Vision, Iet, Ieee vol. 4, 183-194.  
01-09-2010
Relevant PublicationCoupled Prediction Classification for Robust Visual Tracking
Patras I and Hancock ER
Ieee Transactions On Pattern Analysis and Machine Intelligence vol. 32 (9), 1553-1567.  
01-09-2010
bullet iconPyramidal Model for Image Semantic Segmentation
Passino G, Patras I and Izquierdo E
ICPR 2010 Istanbul, Turkey 23 Aug 2010 - 26 Aug 2010., 1554-1557.  
23-08-2010
bullet iconMultiplicative Update Rules for Multilinear Support Tensor Machines
Kotsia I and Patras I
2010 20th International Conference on Pattern Recognition., 33-36.  
01-08-2010
bullet iconRegression-Based Multi-view Facial Expression Recognition
Rudovic O, Patras I and Pantic M
2010 20th International Conference on Pattern Recognition., 4121-4124.  
01-08-2010
bullet iconRelative Margin Support Tensor Machines for gait and action recognition
Kotsia I and Patras I
Proceedings of the ACM International Conference on Image and Video Retrieval., 446-453.  
05-07-2010
bullet iconOptimizing visual search with implicit user feedback in interactive video retrieval
Vrochidis S, Kompatsiaris I and Patras I
Proceedings of the ACM International Conference on Image and Video Retrieval., 274-281.  
05-07-2010
bullet iconFacial Expression Invariant Head Pose Normalization using Gaussian Process Regression
Ognjen R, Ioannis P and Maja P
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops., 28-33.  
01-06-2010
bullet iconCoupled Gaussian Process Regression for Pose-Invariant Facial Expression Recognition
Rudovic O, Patras I and Pantic M
COMPUTER VISION-ECCV 2010, PT II. vol. 6312, 350-363. Editors: Daniilidis K, Maragos P and Paragios N. 
01-01-2010
bullet iconSingle Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos
Koelstra S, Yazdani A, Soleymani M, Muhl C, Lee J-S, Nijholt A, Pun T, Ebrahimi T and Patras I
BRAIN INFORMATICS, BI 2010. vol. 6334, 89-100.  
01-01-2010
bullet iconExploiting implicit user feedback in interactive video retrieval.
Vrochidis S, Kompatsiaris I and Patras I
WIAMIS., 1-4.  
01-01-2010
bullet iconLearning output-kernel-dependent regression for human pose estimation
Guo W and Patras I
British Machine Vision Conference, BMVC 2010 - Proceedings. 
01-01-2010
bullet iconA discriminative voting scheme for object detection using hough forests
Kumar.B.G V and Patras I
British Machine Vision Conference, BMVC 2010 - Proceedings. 
01-01-2010
bullet iconA Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models
Koelstra S, Pantic M and Patras I
Ieee Transactions On Pattern Analysis and Machine Intelligence, Ieee Computer Society vol. 32, 1940-1954-1940-1954.  
01-01-2010

2009

bullet iconSparse B-spline polynomial descriptors for human activity recognition
Oikonomopoulos A, Pantic M and Patras I
Image Vision Comput vol. 27 (12), 1814-1825.  
01-11-2009
bullet iconLatent Semantics Local Distribution for CRF-based Image Semantic Segmentation
Passino G, Patras I and Izquierdo E
BMVC 2009 London, England 7 Sep 2009 - 10 Sep 2009. (26), 1-12. Editors: Cavallaro A, Prince SJD and Alexander D. 
01-09-2009
bullet iconEEG analysis for implicit tagging of video data
Koelstra S, Mühl C and Patras I
2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops., 1-6.  
01-09-2009
bullet iconDiscriminative 3D Human Pose Estimation from Monocular Images via Topological Preserving Hierarchical Affinity Clustering
Guo W and Patras I
2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops., 9-15.  
01-09-2009
bullet iconAn implicit spatiotemporal shape model for human activity localization and recognition
Oikonomopoulos A, Patras I and Pantic M
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops., 27-33.  
01-06-2009
bullet iconA Multimedia Content Semantics Extraction Framework for Enhanced Social Interaction
Passino G, Piatrik T, Patras I and Izquierdo E
EuroITV 2009 Leuven, Belgium 3 Jun 2009 - 5 Jun 2009., 89-91. Editors: Donoso V, Geerts D, Cesar P and De Grooff D. 
01-06-2009
bullet iconAn Implicit Spatiotemporal Shape Model for Human Activity Localization and Recognition
Oikonomopoulos A, Patras I and Pantic M
2009 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPR WORKSHOPS 2009), VOLS 1 AND 2., 786-792.  
01-01-2009
bullet iconTHE FAST-3D SPATIO-TEMPORAL INTEREST REGION DETECTOR
Koelstra S and Patras I
2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES., 242-245.  
01-01-2009
bullet iconFace Pose Analysis
Patras I
In Encyclopedia of Biometrics, Springer Nature 324-329.  
01-01-2009
bullet iconAn implicit spatiotemporal shape model for human activity localization and recognition
Oikonomopoulos A, Patras I and Pantic M
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009., 27-33.  
01-01-2009
bullet iconCONTEXT AWARENESS IN GRAPH-BASED IMAGE SEMANTIC SEGMENTATION VIA VISUAL WORD DISTRIBUTIONS
Passino G, Patras I and Izquierdo E
2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES., 33-36.  
01-01-2009
bullet iconFace Acquisition

In Encyclopedia of Biometrics, Springer Nature 291-291.  
01-01-2009
bullet iconAn Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding
Nikolopoulos S, Papadopoulos GT, Kompatsiaris I and Patras I
MACHINE LEARNING AND DATA MINING IN PATTERN RECOGNITION. vol. 5632, 525-539. Editors: Perner P. 
01-01-2009

2008

bullet iconHuman Gesture Recognition using Sparse B-spline Polynomial Representations
Oikonomopoulos A, Pantic M and Patras I
Belgian/Netherlands Artificial Intelligence Conference., 193-200.  
01-12-2008
bullet iconOn the Role of Structure in Part-based Object Detection
Passino G, Patras I and Izquierdo E
ICIP 2008 San Diego, California 12 Oct 2008 - 15 Oct 2008., 65-68.  
12-10-2008
bullet iconIncremental refinement of image salient-point detection.
Andreopoulos Y and Patras I
Ieee Transactions On Image Processing vol. 17 (9), 1685-1699.  
01-09-2008
bullet iconAspect Coherence for Graph-Based Image Labelling
Passino G, Patras I and Izquierdo E
VIE 2008 Xi’an, China 29 Jul 2008 - 1 Aug 2008., 94-99.  
01-08-2008
bullet iconIncremental salient point detection
Patras I and Andreopoulos Y
2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12., 1337-1340.  
01-01-2008
bullet iconB-spline polynomial descriptors for human activity recognition.
Oikonomopoulos A, Pantic M and Patras I
CVPR Workshops., 1-6.  
01-01-2008
bullet iconB-spline Polynomial Descriptors for Human Activity Recognition
Oikonomopoulos A, Pantic M and Patras I
2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3., 1622-1627.  
01-01-2008
bullet iconON THE ROLE OF STRUCTURE IN PART-BASED OBJECT DETECTION
Passino G, Patras I and Izquierdo E
2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5., 65-68.  
01-01-2008

2007

bullet iconBayesian Confidence Measures for Block-based Motion Estimation
PATRAS I, Lagendijk RL and Hendriks EA
Ieee Trans. Circuits and Systems For Video Technology vol. 17 Issue 8, 988-995.  
01-08-2007
bullet iconProbabilistic confidence measures for block matching motion estimation
Patras I, Hendriks EA and Lagendijk RL
Ieee T Circ Syst Vid vol. 17 (8), 988-995.  
01-08-2007
bullet iconRegression-ased Template Tracking in Presence of Occlusions
PATRAS I and Hancock ER
International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Santorini, Greece. 
01-06-2007
bullet iconTemplate tracking with observation relevance determination
Patras I and Hancock E
2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7., 501-504.  
01-01-2007
bullet iconRegression tracking with data relevance determination
Patras I and Hancock ER
2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8., 2062-2069.  
01-01-2007
bullet iconGaze tracking by using factorized likelihoods particle filtering and stereo vision
Pogalin E, Redert A, Patras I and Hendriks EA
Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings., 57-64. Editors: Pollefeys M and Daniilidis K. 
01-01-2007
bullet iconTrajectory-based representation of human actions
Oikonomopoulos A, Patras I, Pantic M and Paragios N
Artificial Intelligence for Human Computing. vol. 4451, 133-154. Editors: Huang TS, Nijholt A, Pantic M and Pentland A. 
01-01-2007
bullet iconParticle Filtering Tracking Scheme for Trajectory-based Recognition of Human Actions
PATRAS I, Paragios N, Oikonomopoulos A and Pantic M
In Artificial Intelligence For Human Computing, Springer 133-154. Editors: Huang TS, Nijholt A, Pantic M and Pentland A. 
01-01-2007

2006

bullet iconSpatiotemporal salient points for visual recognition of human actions.
Oikonomopoulos A, Patras I and Pantic M
Ieee Trans Syst Man Cybern B Cybern vol. 36 (3), 710-719.  
01-06-2006
bullet iconKernel-based Recognition of Human Actions Using Spatiotemporal Salient Points
PATRAS I, Pantic M and Oikonomopoulos A
Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Workshop on Vision for HCI, New York, USA - June 2006. 
01-06-2006
bullet iconDynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences.
Pantic M and Patras I
Ieee Trans Syst Man Cybern B Cybern vol. 36 (2), 433-449.  
01-04-2006
bullet iconCombining color and shape information for illumination-viewpoint invariant object recognition.
Diplaros A, Gevers T and Patras I
Ieee Trans Image Process vol. 15 (1), 1-11.  
01-01-2006

2005

bullet iconLearning Spatiotemporal Models of Facial Expressions
PATRAS I, Valstar MF and Pantic M
International Conference on Measuring Behaviour, Wageningen - September 2005. 
01-09-2005
bullet iconFacial Action Unit Detection Using Probabilistically Actively Learned Support Vector Machines on Tracked Facial Point Data
PATRAS I, Pantic M and Valstar MF
Proceedings of IEEE International Confernece on Computer Visision and Pattern Recognition, workshop on Vision for HCI, San Diego, USA - June 2005. 
01-06-2005
bullet iconSpatiotemporal saliency for human action recognition
Oikonomopoulos A, Patras I and Pantic M
2005 IEEE International Conference on Multimedia and Expo (ICME), Vols 1 and 2., 430-433.  
01-01-2005
bullet iconDetecting facial actions and their temporal segments in nearly frontal-view face image sequences
Pantic M and Patras I
INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOL 1-4, PROCEEDINGS., 3358-3363.  
01-01-2005
bullet iconTracking deformable motion
Patras I and Pantic M
INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOL 1-4, PROCEEDINGS., 1066-1071.  
01-01-2005

2004

bullet iconDense motion estimation using regularization constraints on local parametric models.
Patras I, Worring M and van den Boomgaard R
Ieee Trans Image Process vol. 13 (11), 1432-1443.  
01-11-2004
bullet iconMultilevel Motion History for Facial Action Detection from Face Video
PATRAS I, Pantic M and Valstar M
IEEE International Conference on Systems, Management and Cybernetics, Den Haag, The Netherlands - October 2005. 
01-10-2004
bullet iconMotion History for Facial Action Detection in Video
Valstar M, Pantic M and Patras I
2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583). vol. 1, 635-640.  
01-01-2004
bullet iconTemporal modeling of facial actions from face profile image sequences
Pantic M and Patras I
2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXP (ICME), VOLS 1-3., 49-52.  
01-01-2004
bullet iconCombining color and shape information for content-based image retrieval on the Internet
Diplaros A, Gevers T and Patras I
INTERNET IMAGING V. vol. 5304, 132-141. Editors: Santini S and Schettini R. 
01-01-2004
bullet iconOnline globally consistent mosaicing using an efficient representation
Winkelman F and Patras I
2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7., 3116-3121.  
01-01-2004
bullet iconFacial action unit recognition using temporal templates
Valstar M, Patras I and Pantic M
RO-MAN 2004: 13TH IEEE INTERNATIONAL WORKSHOP ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION, PROCEEDINGS., 253-258.  
01-01-2004
bullet iconParticle filtering with factorized likelihoods for tracking facial features
Patras I and Pantic M
SIXTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS., 97-102.  
01-01-2004

2003

bullet iconColor-Shape Context for Object Recognition
PATRAS I, Gevers T and Diplaros A
IEEE Workshop on Color and Photometric Methods in Computer Vision (in conjunction with ICCV 2003), Nice, France. 
01-07-2003
bullet iconSemi-automatic object-based video segmentation with labeling of color segments
Patras I, Hendriks EA and Lagendijk RL
Signal Process-Image vol. 18 (1), 51-65.  
01-01-2003

2002

bullet iconTREC Feature Extraction by Active Learning
PATRAS I, Raaijmakers S, Snoek C, van Rest J, Worring M, van Leeuwen D, den Hartog J and Vendring J
11th Text Retrieval Confernece (TREC), Gaithersburg, MD - November 2002. 
01-11-2002
bullet iconRegularized patch motion estimation
Patras I and Worring M
16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL I, PROCEEDINGS., 323-326. Editors: Kasturi R, Laurendeau D and Suen C. 
01-01-2002
bullet iconFacial action recognition in face profile image sequences
Pantic M, Patras I and Rothkrantz L
IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I AND II, PROCEEDINGS., 37-40.  
01-01-2002
bullet iconConfidence measures for block matching motion estimation
Patras I, Hendriks EA and Lagendijk RL
2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS., 277-280.  
01-01-2002

2001

bullet iconVideo segmentation by MAP labeling of watershed segments
Patras I, Hendriks EA and Lagendijk RL
Ieee T Pattern Anal vol. 23 (3), 326-332.  
01-03-2001
bullet iconRobust Region Merging for Motion Based Sementation Using the Kolmogorov-Smirnov Test
PATRAS I, Hendriks EA, Broekhoven M and Hupkens T
Image Processing and Communications vol. 6 (3-4), 27-34.  
01-01-2001
bullet iconLazy Users and Automatic Video Retrieval Tools in (the) Lowlands
PATRAS I, List J, Geusebroek J-M, den Hartog J, Hiemstra D, van Ballegooij A, Worring M, Snoek C, Raaijmakers S, Todoran L, Vendrig J, de Vries A, Westerveld T and Baan J
Proceedings of the 10th Text Retrieval Conference (TREC), NIST 2001. 
01-01-2001

1998

bullet iconIterative motion estimation - segmentation method using watershed segments
Patras I, Hendriks EA and Lagendijk RL
IEEE International Conference on Image Processing. vol. 2, 642-646.  
01-12-1998

1997

bullet iconConstruction of multiple views using jointly estimated motion and disparity fields
Patras IK, Hendriks EA and Tziritas GG
Visual Communications and Image Processing '97. vol. 3024, 380-390.  
10-01-1997

Grants

solid heart iconGrants of specific relevance to the Centre for Multimodal AI
solid heart iconAI4MEDIA: Patras (PI)
Ioannis Patras
£245,072 EU Commission - Horizon 2020
01-09-2020 - 31-08-2024
solid heart iconDeep Learning from Crawled Spatio-Temporal Representations of Visual Data
Ioannis Patras
£358,043 EPSRC Engineering and Physical Sciences Research Council
01-07-2018 - 31-12-2021
solid heart iconNewton Mobility Grant
Ioannis Patras
£12,000 Royal Society
10-03-2017 - 10-03-2019
solid heart iconHuman Action Analysis
Ioannis Patras
£180,000 Yamaha Corporation
01-01-2017 - 28-02-2019