Integrating Video-Language Model with Mixture of Low-Rank Experts for Video Commonsense Captioning
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.11.2026 · 22 (11) · 1-24
DOI: 10.1145/3857795 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 11.11.2026. Verfasst von Yiping Yang und 1 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mobile Information Networks National Science and Technology Major Project, Key Research and Development Program of Zhejiang Province.
Abstract (Originalsprache)
The video commonsense captioning task aims to generate descriptive textual captions that encapsulate not only visible content but also underlying events and their inherent commonsense. Unlike traditional video captions, which merely describe visible objects and actions, video commonsense captioning provides deeper insights. However, current research on video commonsense reasoning still faces challenges. Existing studies often focus on understanding explicit video content, and there is still a need to bridge the complex semantic gap between visible video content and intangible commonsense knowledge. Hence, we propose a novel and affordable solution. By leveraging the commonsense knowledge within large language models, we construct a Video-Language Model with Mixture of Low-Rank Adaptation Experts (VLM-MOLAE) that excels in understanding videos and performing commonsense reasoning. Specifically, we first utilize a pre-trained large language model as the backbone, which enables us to exploit its commonsense knowledge to facilitate comprehension and inference. Further, a transformer-based video embedder module is specially designed to extract video features to be aligned with the LLM input space. Additionally, a parameter-efficient mixture of experts module is developed to adapt the large language model with low-rank experts, enabling precise reasoning for diverse inputs. Extensive experiments and analyses conducted on a benchmark dataset demonstrate the effectiveness and superiority of our proposed model. The code is publicly available at https://github.com/gxytsyt/VLM_MOLAE .
Förderung
- Mobile Information Networks National Science and Technology Major Project
- Key Research and Development Program of Zhejiang Province
Zitieren
APA
Yang, Y., & Li, Y. (2026). Integrating Video-Language Model with Mixture of Low-Rank Experts for Video Commonsense Captioning. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(11), 1-24. https://doi.org/10.1145/3857795
Vancouver
Yang Y, Li Y. Integrating Video-Language Model with Mixture of Low-Rank Experts for Video Commonsense Captioning. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(11):1-24. doi:10.1145/3857795
BibTeX
@article{Yang2026,
author = {Yang, Yiping and Li, Yingming},
title = {Integrating Video-Language Model with Mixture of Low-Rank Experts for Video Commonsense Captioning},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {11},
pages = {1--24},
doi = {10.1145/3857795}
}
EUVIMED