3 papers
cs.CV2026
Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Wang Chen, Yuhui Zeng, Yongdong Luo +5
Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically sel…
cs.CV2026
Event-Anchored Frame Selection for Effective Long-Video Understanding
Wang Chen, Yongdong Luo, Yuhui Zeng +5
Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approa…
cs.CV2025
Synthetic-to-Real Camouflaged Object Detection
Zhihao Luo, Luojun Lin, Zheng Lin
Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the av…