Dr Georgios Tzimiropoulos
Senior Lecturer
School of Electronic Engineering and Computer Science
Queen Mary University of London
Queen Mary University of London
Research
Computer Vision, Deep Learning
Interests
My research interests are mainly in the problems of image & video recognition, detection and tracking, pose estimation, image & video generation, 3D reconstruction and super-resolution, with humans and their actions being the focal point of my research. I have approached these problems mainly using tools from Mathematical Optimization and Machine Learning. My current focus is on Compute & Data Efficient Deep Learning and its application to video recognition.Publications
Publications of specific relevance to the Centre for Multimodal AI2024
Ntinou I, Sanchez E and Tzimiropoulos G (2024). Memsvd: Long-Range Temporal Structure Capturing Using Incremental SVD. 2024 IEEE International Conference on Image Processing (ICIP). 30-10-2024
Maniadis Metaxas I, Tzimiropoulos G and Patras I (2024). Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing. European Conference on Computer Vision 2024 29 Sep 2024 - 4 Oct 2024. 29-09-2024
Sun Z, Song S, Patras I and Tzimiropoulos G (2024). CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition. 01-01-2024
Bulat A, Ouali Y, Guerrero R, Martinez B and Tzimiropoulos G (2024). Efficient Vision-Language pre-training via domain-specific learning for human activities. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 01-01-2024
2023
Bulat A and Tzimiropoulos G (2023). Language-Aware Soft Prompting: Text-to-Text Optimization for Fewand
Zero-Shot Adaptation of V&L Models. International Journal of Computer Vision, Springer 26-10-2023
Ouali Y, Bulat A, Martinez B and Tzimiropoulos G (2023). Black Box Few-Shot Adaptation for Vision-Language models. International Conference on Computer Vision. 02-10-2023
Bulat A, Guerrero R, Martinez B and Tzimiropoulos G (2023). Fs-detr: Few-shot detection transformer with prompting and without re-training. International Conference on Computer Vision. 02-10-2023
Bulat A, Sanchez E, Martinez B and Tzimiropoulos G (2023). ReGen: A good Generative zero-shot video classifier should be Rewarded. International Conference on Computer Vision. 02-10-2023
Bounareli S, TZELEPIS C, Argyriou V, Patras I and Tzimiropoulos G (2023). HyperReenact: one-shot reenactment via jointly learning to refine and retarget faces. International Conference on Computer Vision. 02-10-2023
Derakhshani MM, Sanchez E, Bulat A, Turrisi da Costa VG, Snoek CGM, Tzimiropoulos G and Martinez B (2023). Bayesian Prompt Learning for Image-Language Model Generalization. International Conference on Computer Vision. 02-10-2023
Bulat A and Tzimiropoulos G (2023). LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24-06-2023
Mallis D, Sanchez E, Bell M and Tzimiropoulos G (2023). From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers 04-01-2023
Xenos A, Stafylakis T, Patras I and Tzimiropoulos G (2023). A Simple Baseline for Knowledge-Based Visual Question Answering., Editors: Bouamor H, Pino J and Bali K. 01-01-2023
2022
Sun Z and Tzimiropoulos G (2022). Part-based Face Recognition with Vision
Transformers. British Machine Vision Conference. 21-11-2022
Bounareli S, Argyriou V and Tzimiropoulos G (2022). Finding Directions in GAN’s Latent Space for
Neural Face Reenactment. British Machine Vision Conference. 21-11-2022
Pan J, Bulat A, Tan F, Zhu X, Dudziak L, Li H, Tzimiropoulos G and Martinez B (2022). EdgeViTs: Competing Light-weight CNNs onMobile Devices with Vision Transformers. European Conference on Computer Vision. 25-10-2022
Bulat A, Cheng S, Yang J, Garbett A, Sanchez E and Tzimiropoulos G (2022). Pre-training strategies and datasets for facial representation learning. European Confence on Computer Vision. 25-10-2022
2021
Bulat A, Perez-Rua J-M, Sudhakaran S, Martinez B and Tzimiropoulos G (2021). Space-time Mixing Attention for Video Transformer. Thirty-fifth Conference on Neural Information Processing Systems. 06-12-2021
Tzelepis C, Tzimiropoulos G and Patras I (2021). WarpedGANSpace: Finding non-linear RBF paths in GAN latent space. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 17-10-2021
Bulat A and Tzimiropoulos G (2021). Bit-Mixer: Mixed-precision networks with runtime bit-width selection. International Conference on Computer Vision (ICCV) 11 Oct 2021 - 17 Oct 2021. 11-10-2021
Sanchez E, Tellamekala MK, Valstar M and Tzimiropoulos G (2021). Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition 19 Jun 2021 - 25 Jun 2021. 21-06-2021
Yang J, Martinez B, Bulat A and Tzimiropoulos G (2021). Knowledge distillation via softmax regression representation learning. International Conference on Learning Representations (ICLR). 04-05-2021
Bulat A, Martinez B and Tzimiropoulos G (2021). High-Capacity Expert Binary Networks. International Conference on Learning Representations (ICLR). 04-05-2021
Song S, Jaiswal S, Sanchez E, Tzimiropoulos G, Shen L and Valstar M (2021). Self-supervised Learning of Person-specific Facial Dynamics for Automatic Personality Recognition. IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers 09-03-2021
Ntinou IN, Sanchez E, Bulat A, Tzimiropoulos G and Valstar M (2021). A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation. IEEE Transactions on Affective Computing 23-02-2021
2020
Dimitrios M, Enrique S, Matt B and Tzimiropoulos G (2020). Unsupervised Learning of Object Landmarks via Self-Training Correspondence. Advances in Neural Information Processing Systems (NeurIPS) 6 Dec 2020 - 12 Dec 2020. 06-12-2020
Bulat A, Martinez B and Tzimiropoulos G (2020). BATS: Binary ArchitecTure Search. European Conference on Computer Vision (ECCV) 23 Aug 2020 - 28 Aug 2020. 24-08-2020
Khan MH, McDonagh J, Khan S, Shahabuddin M, Arora A, Khan FS, Shao L and Tzimiropoulos G (2020). AnimaWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13-06-2020
Yang J, Bulat A and Tzimiropoulos G (2020). FAN-Face: a Simple Orthogonal Improvement to Deep Face Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI) vol. 34 (07), 12621-12628. 03-04-2020
2019
Kossaifi J, Bulat A, Tzimiropoulos G and Pantic M (2019). T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20-06-2019
2018
Bulat A and Tzimiropoulos G (2018). Hierarchical Binary CNNs for Landmark Localization with Limited Resources. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers vol. 42 (2), 343-356. 23-08-2018
2017
Jackson AS, Bulat A, Argyriou V and Tzimiropoulos G (2017). Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression. IEEE International Conference on Computer Vision. 22-12-2017
Bulat A and Tzimiropoulos G (2017). How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks). 2017 IEEE International Conference on Computer Vision (ICCV). 01-10-2017
Sanchez-Lozano E, Tzimiropoulos G, Martinez B, Torre FDL and Valstar M (2017). A Functional Regression Approach to Facial Landmark Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers vol. 40 (9), 2037-2050. 29-08-2017
2016
Bulat A and Tzimiropoulos G (2016). Human pose estimation via convolutional part heatmap regression. https://link.springer.com/conference/eccv. 16-09-2016
Bulat A and Tzimiropoulos Y (2016). Convolutional aggregation of local evidence for large pose face alignment. Procedings of the British Machine Vision Conference 2016. 01-01-2016
2014
Tzimiropoulos G and Pantic M (2014). Gauss-Newton deformable part models for face alignment in-the-wild. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 25-09-2014
Grants
Grants of specific relevance to the Centre for Multimodal AIReliable AI and Data OptimisationGeorgios Tzimiropoulos
£339,312 EPSRC - EU Scheme (01-01-2024 - 31-12-2026)