ICIP 2023

SELF-SUPERVISED 3D SKELETON REPRESENTATION LEARNING WITH ACTIVE SAMPLING AND ADAPTIVE RELABELING FOR ACTION RECOGNITION

HOKEM: HUMAN AND OBJECT KEYPOINT-BASED EXTENSION MODULE FOR HUMAN-OBJECT INTERACTION DETECTION

Dual Temporal Transformers for Fine-Grained Dangerous Action Recognition

FEATURE SPACE DATA AUGMENTATION FOR VIEWPOINT-ROBUST ACTION RECOGNITION IN VIDEOS

FREQUENCY ENHANCEMENT NETWORK FOR EFFICIENT COMPRESSED VIDEO ACTION RECOGNITION

SELF-SUPERVISED CONTRASTIVE LEARNING FOR AUDIO-VISUAL ACTION RECOGNITION

Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention

ACTION ANTICIPATION WITH GOAL CONSISTENCY

SCRATCHHOI: TRAINING HUMAN-OBJECT INTERACTION DETECTORS FROM SCRATCH

Multi-scale temporal feature fusion for few-shot action recognition

Implicit Attention-based Cross-modal Collaborative Learning for Action Recognition

A BASELINE ON CONTINUAL LEARNING METHODS FOR VIDEO ACTION RECOGNITION