News

CMAI in the AAAI conference 2025 (https://aaai.org/conference/aaai/aaai-25/)

4 papers from the Centre of Multimodal AI have been accepted and are to be presented in the main conference:

Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval, Dezhao Luo, Shaogang Gong, Jiabo Huang, Hailin Jin, Yang Liu. https://arxiv.org/pdf/2401.13329

InvSeg: Test-Time Prompt Inversion for Semantic Segmentation, Jiayi Lin, Jiabo Huang, Jian Hu, Shaogang Gong. https://arxiv.org/pdf/2410.11473

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks, Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel R.D. Rodrigues https://arxiv.org/abs/2402.02629

Text2MIDI: Generating Symbolic Music from Captions, by Keshav Bhandari, Abhinaba Roy, Kyra Wang, Geeta Puri, Simon Colton, and Dorien Herremans https://arxiv.org/abs/2412.16526