EUVIMEDEUVIMED entdecken
Crossref

ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding

Yuan Zhou, Litao Hua, Shilong Jin, Wentao Huang, Haoran Duan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13791-13799

DOI: 10.1609/aaai.v40i16.38387 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuan Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on effective keyframes that are not only informative but also causally decisive. To this end, we propose Reinforced Causal Search with Information Bottleneck (ReaSon), a framework that formulates keyframe selection as an optimization problem with the help of a novel Causal Information Bottleneck (CIB), which explicitly defines keyframes as those satisfying both predictive sufficiency and causal necessity. Specifically, ReaSon employs a learnable policy network to select keyframes from a visually relevant pool of candidate frames to capture predictive sufficiency, and then assesses causal necessity via counterfactual interventions. Finally, a composite reward aligned with the CIB principle is designed to guide the selection policy through reinforcement learning. Extensive experiments on NExT-QA, EgoSchema, and Video-MME demonstrate that ReaSon consistently outperforms existing state-of-the-art methods under limited-frame settings, validating its effectiveness and generalization ability.

Zitieren

APA

Zhou, Y., Hua, L., Jin, S., Huang, W., & Duan, H. (2026). ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13791-13799. https://doi.org/10.1609/aaai.v40i16.38387

Vancouver

Zhou Y, Hua L, Jin S, Huang W, Duan H. ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13791-13799. doi:10.1609/aaai.v40i16.38387

BibTeX
@article{Zhou2026,
  author = {Zhou, Yuan and Hua, Litao and Jin, Shilong and Huang, Wentao and Duan, Haoran},
  title = {ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {16},
  pages = {13791--13799},
  doi = {10.1609/aaai.v40i16.38387}
}
Kostenlos starten →