VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Authors:
Preprint
- 18 December 2024
- preprint
- Published by Qeios Ltd in Qeios Preprints
Abstract
Recent researches on video large language models (VideoLLM) predominantly focus on model architectures and training datasets, leaving the interaction format between the user and the model under-explored. In existing works, users often interact with VideoLLMs by using the entire video and a query as input, after which the model generates a response. This interaction format constrains the application of VideoLLMs in scenarios such as live-streaming comprehension where videos do not end and responses are required in a real-time manner, and also results in unsatisfactory performance on time-sensitive tasks that requires localizing video segments. In this paper, we focus on a video-text duet interaction format. This interaction format is characterized by the continuous playback of the video, and both the user and the model can insert their text messages at any position during the video playback. When a text message ends, the video continues to play, akin to the alternative of two performers in a duet. We construct MMDuetIT, a video-text training dataset designed to adapt VideoLLMs to video-text duet interaction format. We also introduce the Multi-Answer Grounded Video Question Answering (MAGQA) task to benchmark the real-time response ability of VideoLLMs. Trained on MMDuetIT, MMDuet demonstrates that adopting the video-text duet interaction format enables the model to achieve significant improvements in various time-sensitive tasks (76% CIDEr on YouCook2 dense video captioning, 90% mAP on QVHighlights highlight detection and 25% R@0.5 on Charades-STA temporal video grounding) with minimal training efforts, and also enable VideoLLMs to reply in a real-time manner as the video plays. Code, data and demo are available at: https://github.com/yellow-binary-tree/MMDuet.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- InternVideo2: Scaling Foundation Models for Multimodal Video Understanding2024
- ST-LLM: Large Language Models Are Effective Temporal Learners2024
- Can I Trust Your Answer? Visually Grounded Video Question Answering2024
- MVBench: A Comprehensive Multi-modal Video Understanding Benchmark2024
- VTimeLLM: Empower LLM to Grasp Video Moments2024
- TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding2024
- VideoLLM-online: Online Video Large Language Model for Streaming Video2024
- Hierarchical Video-Moment Retrieval and Step-Captioning2023
- Ego4D: Around the World in 3,000 Hours of Egocentric Video2022
- COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis2019