4 papers
Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
Yulin Li, Haokun Gui, Ziyang Fan +4
Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computat…
CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval
Bin Kang, Bin Chen, Junjie Wang +3
Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggreg…
Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
Junjie Wang, Keyu Chen, Yulin Li +4
Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbou…
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Junjie Wang, Bin Chen, Yulin Li +3
Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbou…