Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

Research paper by Yunlong Tang and collaborators. Published 2025-04-07. Topics: SAMURAI, TRACE-Uni, InternVL-2.5, spatiotemporal visual prompts, chain-of-thought reasoning.

By Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng, Junjia Guo, Zhuo Liu, Luchuan Song, Ali Vosoughi, Jinxi He, Liu He, Zeliang Zhang, Jiebo Luo, Chenliang XuResearch paper

Resource information

Authors: Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng, Junjia Guo, Zhuo Liu, Luchuan Song, Ali Vosoughi, Jinxi He, Liu He, Zeliang Zhang, Jiebo Luo, Chenliang Xu
Research topics: SAMURAI, TRACE-Uni, InternVL-2.5, spatiotemporal visual prompts, chain-of-thought reasoning, object segmentation, event boundary detection, temporal analysis, object-centric descriptions, temporal sensitivity, flexible user interactions, temporal coherence
Publication date: 2025-04-07
Publication: arXiv
Last record update: Nov 3, 2026