Qingchao Chen

Latest

• ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding
• Training-free Video Temporal Grounding usingLarge-scale Pre-trained Models
• Phrase-Level Temporal Relationship Mining for Temporal Sentence Localization
• Weakly Supervised Temporal Sentence Grounding with Gaussian-based Contrastive Proposal Learning
• Weakly Supervised Video Moment Localization with Contrastive Negative Sample Mining