VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
- URL: http://arxiv.org/abs/2411.17991v1
- Date: Wed, 27 Nov 2024 02:15:34 GMT
- Title: VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
- Authors: Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao,
- Abstract summary: 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.
In this paper, we focus on a video-text duet interaction format.
We construct MMDuetIT, a video-text training dataset designed to adapt VideoLLMs to video-text duet interaction format.
- Score: 40.66959827210223
- License:
- 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.
Related papers
- InternVideo2: Scaling Foundation Models for Multimodal Video Understanding [51.129913789991924]
InternVideo2 is a new family of video foundation models (FM) that achieve state-of-the-art results in video recognition, video-speech tasks, and video-centric tasks.
Our core design is a progressive training approach that unifies the masked video modeling, cross contrastive learning, and prediction token, scaling up to 6B video size.
arXiv Detail & Related papers (2024-03-22T17:57:42Z) - TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding [20.037781644877388]
TimeChat is a time-sensitive multimodal large language model specifically designed for long video understanding.
Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths.
arXiv Detail & Related papers (2023-12-04T17:09:52Z) - Multi-event Video-Text Retrieval [33.470499262092105]
Video-Text Retrieval (VTR) is a crucial multi-modal task in an era of massive video-text data on the Internet.
We introduce the Multi-event Video-Text Retrieval (MeVTR) task, addressing scenarios in which each video contains multiple different events.
We present a simple model, Me-Retriever, which incorporates key event video representation and a new MeVTR loss for the MeVTR task.
arXiv Detail & Related papers (2023-08-22T16:32:46Z) - Towards Fast Adaptation of Pretrained Contrastive Models for
Multi-channel Video-Language Retrieval [70.30052749168013]
Multi-channel video-language retrieval require models to understand information from different channels.
contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text.
There is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources.
arXiv Detail & Related papers (2022-06-05T01:43:52Z) - BridgeFormer: Bridging Video-text Retrieval with Multiple Choice
Questions [38.843518809230524]
We introduce a novel pretext task dubbed Multiple Choice Questions (MCQ)
A module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features.
In the form of questions and answers, the semantic associations between local video-text features can be properly established.
Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets.
arXiv Detail & Related papers (2022-01-13T09:33:54Z) - CLIP2Video: Mastering Video-Text Retrieval via Image CLIP [13.270902407320005]
We present CLIP2Video network to transfer the image-language training model to video-text retrieval in an end-to-end manner.
We conduct thorough ablation studies, and achieve state-of-the-art performance on text-to-video and video-to-text retrieval benchmarks.
arXiv Detail & Related papers (2021-06-21T13:30:33Z) - Video Corpus Moment Retrieval with Contrastive Learning [56.249924768243375]
Video corpus moment retrieval (VCMR) is to retrieve a temporal moment that semantically corresponds to a given text query.
We propose a Retrieval and Localization Network with Contrastive Learning (ReLoCLNet) for VCMR.
Experimental results show that ReLoCLNet encodes text and video separately for efficiency, its retrieval accuracy is comparable with baselines adopting cross-modal interaction learning.
arXiv Detail & Related papers (2021-05-13T12:54:39Z) - Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [80.7397409377659]
We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets.
Our model is flexible and can be trained on both image and video text datasets, either independently or in conjunction.
We show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks.
arXiv Detail & Related papers (2021-04-01T17:48:27Z) - HERO: Hierarchical Encoder for Video+Language Omni-representation
Pre-training [75.55823420847759]
We present HERO, a novel framework for large-scale video+language omni-representation learning.
HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer.
HERO is jointly trained on HowTo100M and large-scale TV datasets to gain deep understanding of complex social dynamics with multi-character interactions.
arXiv Detail & Related papers (2020-05-01T03:49:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.