4 papers · 1 filter
YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detection
Yiyu Liu, Shuo Ye, Chao Hao +1
Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models against erratic motion dynamics. E…
Distribution-Specific Learning for Joint Salient and Camouflaged Object Detection
Chao Hao, Zitong Yu, Xin Liu +5
Salient object detection (SOD) and camouflaged object detection (COD) are two closely related but distinct computer vision tasks. Although both are class-agnostic segmentation task…
TRRG: Towards Truthful Radiology Report Generation With Cross-modal Disease Clue Enhanced Large Language Model
Yuhao Wang, Chao Hao, Yawen Cui +4
The vision-language modeling capability of multi-modal large language models has attracted wide attention from the community. However, in medical domain, radiology report generatio…
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
Xin Liu, Chao Hao, Zitong Yu +2
The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and t…