Yabing Wang

6

Papers

5

Total Citations

Papers (6)

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning

Moment Quantization for Video Temporal Grounding

RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension

CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer