Human-centric multimedia and human-machine interaction

Surface-Sampling based Objective Quality Assessment Metrics for Meshes

GAZE PRE-TRAIN FOR IMPROVING DISPARITY ESTIMATION NETWORKS

Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities

Toward privacy-enhancing ambulatory-based well-being monitoring: Investigating user re-identification risk in multimodal data

Contrastive Self-Supervised Learning for Automated Multi-Modal Dance Performance Assessment

Salient Co-Speech Gesture Synthesizing with Discrete Motion Representation

GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network