5 papers
SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation
Jiangshan Gong, Yuqun Wu, Qiqian Fu +4
Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typical…
Hints, Critics, and Teachers: Prior Injection for Sparse-Reward RL in Vision-Language Math Reasoning
Qiqian Fu
Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answers 3.6% of rollouts correctly…
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
Yao Xiao, Qiqian Fu, Heyi Tao +3
Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like…
Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Driving
Yizhou Wang, Jen-Hao Cheng, Jui-Te Huang +8
Sensor fusion is crucial for an accurate and robust perception system on autonomous vehicles. Most existing datasets and perception solutions focus on fusing cameras and LiDAR. How…
FrameRS: A Video Frame Compression Model Composed by Self supervised Video Frame Reconstructor and Key Frame Selector
Qiqian Fu, Guanhong Wang, Gaoang Wang
In this paper, we present frame reconstruction model: FrameRS. It consists self-supervised video frame reconstructor and key frame selector. The frame reconstructor, FrameMAE, is d…