Self-Supervised Visual Representation Learning via Residual Momentum

DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning

Joint Path Alignment Framework for 3D Human Pose and Shape Estimation From Video

CE-BART: Cause-and-Effect BART for Visual Commonsense Generation

LAD: A Hybrid Deep Learning System for Benign Paroxysmal Positional Vertigo Disorders Diagnostic

Deep learning-based noise robust flexible piezoelectric acoustic sensors for speech processing

Dual-Scale Doppler Attention for Human Identification

Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning

Fair Facial Attribute Classification via Causal Graph-Based Attribute Translation

Seamless equal accuracy ratio for inclusive CTC speech recognition