EUVIMEDEUVIMED entdecken
Crossref

Rethinking Video-Language Model from the Language Input Perspective

Xiang Fang, Wanlong Fang, Changshuo Wang, Xiaoye Qu, Daizong Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3885-3893

DOI: 10.1609/aaai.v40i5.37390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiang Fang und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driven by the wave of large language models, Video-Language Models (VLMs) have become a significant yet challenging technology to bridge the gap between videos and texts. Although previous VLM works have made significant progress, almost all of them implicitly assume that all the texts are predefined by the specific template. In real-world applications, such a strict assumption is impossible to satisfy since 1) predefining all the texts is extremely time-consuming and labor-intensive. 2) these predefined text inputs are too restrictive and user-unfriendly, limiting their applications. It is observed that given a video input, texts with similar semantics but different templates lead to various performances. To this end, in this paper, we propose a novel plug-and-play framework for various VLM-based methods to fully bridge videos and texts. Specifically, we first generate positive and negative texts from the original ones to target specific text components. Then, we propose an attribute-based text reasoning strategy to mine fine-grained textual semantics of generated texts. Finally, we utilize videos as guidance to conduct cross-modal bridging by designing a self-weighted loss. Extensive experiments show that the proposed method can serve as the plug-and-play module to effectively improve the performance of state-of-the-art VLMs.

Zitieren

APA

Fang, X., Fang, W., Wang, C., Qu, X., & Liu, D. (2026). Rethinking Video-Language Model from the Language Input Perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3885-3893. https://doi.org/10.1609/aaai.v40i5.37390

Vancouver

Fang X, Fang W, Wang C, Qu X, Liu D. Rethinking Video-Language Model from the Language Input Perspective. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3885-3893. doi:10.1609/aaai.v40i5.37390

BibTeX
@article{Fang2026,
  author = {Fang, Xiang and Fang, Wanlong and Wang, Changshuo and Qu, Xiaoye and Liu, Daizong},
  title = {Rethinking Video-Language Model from the Language Input Perspective},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3885--3893},
  doi = {10.1609/aaai.v40i5.37390}
}
Kostenlos starten →