3 papers
cs.CV2026
PercepCap: Video Captioner with Structured Spatio-Temporal Perception
Yifan Xu, Zihao Wang, Zhixiao Wang +6
Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occ…
cs.CV2026
SAM 2++: Tracking Anything at Any Granularity
Jiaming Zhang, Cheng Liang, Yichun Yang +7
Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limits their generalization, prevent…
cs.CV2025
CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval
Yifan Xu, Xinhao Li, Yichun Yang +3
Video understanding, including video captioning and retrieval, is still a great challenge for video-language models (VLMs). The existing video retrieval and caption benchmarks only…