EUVIMEDEUVIMED entdecken
Crossref

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

Yolo Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng, Junjia Guo, Zhuo Liu und 7 weitere

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41697-41699

DOI: 10.1609/aaai.v40i48.42385 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yolo Yunlong Tang und 18 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, we introduce CAT-V (Caption Anything in Video), a training-free framework for fine-grained object-centric video captioning of user-selected instances. CAT-V combines (i) a SAMURAI-based Segmenter for precise object masks across frames, (ii) a TRACE-Uni Temporal Analyzer for event boundary detection and coarse event descriptions, and (iii) an InternVL-2.5 Captioner that, conditioned on spatiotemporal visual prompts and chain-of-thought (CoT) guidance, produces detailed, temporally coherent captions about object attributes, actions, states, interactions, and context. The system supports point, box, and region prompts and maintains temporal sensitivity by tracking object states across segments. In contrast to vanilla video captioning that is overly abstract and dense video captioning that is often terse, CAT-V enables object-level specificity with spatial accuracy and temporal coherence, without additional training data.

Zitieren

APA

Tang, Y. Y., Bi, J., Huang, C., Liang, S., Shimada, D., Hua, H., Xiao, Y., Song, Y., Liu, P., Feng, M., Guo, J., Liu, Z., Song, L., Vosoughi, A., He, J., He, L., Zhang, Z., Luo, J., & Xu, C. (2026). Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41697-41699. https://doi.org/10.1609/aaai.v40i48.42385

Vancouver

Tang YY, Bi J, Huang C, Liang S, Shimada D, Hua H, et al. Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41697-41699. doi:10.1609/aaai.v40i48.42385

BibTeX
@article{Tang2026,
  author = {Tang, Yolo Yunlong and Bi, Jing and Huang, Chao and Liang, Susan and Shimada, Daiki and Hua, Hang and Xiao, Yunzhong and Song, Yizhi and Liu, Pinxin and Feng, Mingqian and Guo, Junjia and Liu, Zhuo and Song, Luchuan and Vosoughi, Ali and He, Jinxi and He, Liu and Zhang, Zeliang and Luo, Jiebo and Xu, Chenliang},
  title = {Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41697--41699},
  doi = {10.1609/aaai.v40i48.42385}
}
Kostenlos starten →