Image and video representation

Collaborative Audio-Visual Event Localization based on Sequential Decision and Cross-modal Consistency

Dynamic Scalable Self-Attention Ensemble for Task-Free Continual Learning

StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking

Compressing Cross-Domain Representation via Lifelong Knowledge Distillation

Efficient Feature Extraction for Non-Maximum Suppression in Visual Person Detection

Boundary Cue Guidance and Contextual Feature Mining for Glass Segmentation

Enhancing Multimodal Alignment with Momentum Augmentation for Dense Video Captioning

TOP-K VISUAL TOKENS TRANSFORMER: SELECTING TOKENS FOR VISIBLE-INFRARED PERSON RE-IDENTIFICATION

SINE: SIMILARITY-REGULARIZED INTRA-CLASS EXPLOITATION FOR CROSS-GRANULARITY FEW-SHOT LEARNING

Class-Aware Contextual Information for Semantic Segmentation

COMBINING THE SILHOUETTE AND SKELETON DATA FOR GAIT RECOGNITION

MODIFY: Model-driven Face Stylization without Style Images