Understanding Long Videos with Multimodal Language Models
Keywords: long-video, visual question answering, interpretability
TL;DR: Investigates effects of LLM strengths on Long Video QnA tasks. Introduces Multimodal Video Understanding (MVU) framework that incorporates object-centric data from pre-trained models and sets a new state-of-the-art in long-video tasks.
Abstract: Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of LLMs influence evaluations on standard long video benchmarks. Surprisingly, we discover that LLM-based models yield surprisingly good accuracy on long-video tasks with limited video information, sometimes even with no video specific information.
Building on this, we inject video-specific object-centric information extracted from off-the-shelf pre-trained models into an LLM-based setup. We utilize natural language as a medium for fusing this information. Our resulting Multimodal Video Understanding (MVU) framework demonstrates state-of-the-art performance across long-video understanding benchmarks as well as on robotics domain tasks. Our code will be released publicly.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 811
Loading