5 papers
Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition
Meng-zhu Li, Quanxing Zha, Hongjun Wu
Dynamic Facial Expression Recognition (DFER) facilitates the understanding of psychological intentions through non-verbal communication. Existing methods struggle to manage irrelev…
Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
Zhixuan Wu, Quanxing Zha, Teng Wang +6
Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solutions struggle to effectively…
Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
Wenbin Xing, Quanxing Zha, Lizheng Zu +3
Current research on video hallucination mitigation primarily focuses on isolated error types, leaving compositional hallucinations, arising from incorrect reasoning over multiple i…
Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
Yong Deng, Guoqing Wang, Zhenzhe Ying +12
Large language models (LLMs) exhibit remarkable problem-solving abilities, but struggle with complex tasks due to static internal knowledge. Retrieval-Augmented Generation (RAG) en…
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning
Quanxing Zha, Xin Liu, Shu-Juan Peng +3
Can we accurately identify the true correspondences from multimodal datasets containing mismatched data pairs? Existing methods primarily emphasize the similarity matching between…