2 citations · 3 across the 5 of their papers we have counts for
5 papers
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…
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…
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…
MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization
Zhaozhe Hu, Jia-Li Yin, Bin Chen +3
Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous resear…
Periodically Exchange Teacher-Student for Source-Free Object Detection
Qipeng Liu, Luojun Lin, Zhifeng Shen +1
Source-free object detection (SFOD) aims to adapt the source detector to unlabeled target domain data in the absence of source domain data. Most SFOD methods follow the same self-t…