Signal processing for images and video modeling

DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking

ROBUST CONTENT-VARIANT REFERENCE IMAGE QUALITY ASSESSMENT VIA SIMILAR PATCH MATCHING

Dual-Feature Enhancement for Weakly Supervised Temporal Action Localization

Stochastic super-resolution for Gaussian textures

Semantically-informed Deep Neural Networks for sound recognition

Multimodal Facial Action Unit Detection with Physiological Signals

ON DESIGNING LIGHT-WEIGHT OBJECT TRACKERS THROUGH NETWORK PRUNING: USE CNNS OR TRANSFORMERS?

Unsupervised Action Segmentation of Untrimmed Egocentric Videos

FLOWPOSE: CONDITIONAL NORMALIZING FLOWS FOR 3D HUMAN POSE AND SHAPE ESTIMATION FROM MONOCULAR VIDEOS

SELF-SUPERVISED AUDIO-VISUAL SPEECH REPRESENTATIONS LEARNING BY MULTIMODAL SELF-DISTILLATION

VIDEO CAPTIONING VIA RELATION-AWARE GRAPH LEARNING