Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
- URL: http://arxiv.org/abs/2402.03161v3
- Date: Mon, 3 Jun 2024 08:09:09 GMT
- Title: Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
- Authors: Yang Jin, Zhicheng Sun, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang Song, Kun Gai, Yadong Mu,
- Abstract summary: Video pre-training is challenging due to the modeling of its dynamics video.
In this paper, we address such limitations in video pre-training with an efficient video decomposition.
Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
- Score: 52.63845811751936
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its spatiotemporal dynamics. In this paper, we address such limitations in video-language pre-training with an efficient video decomposition that represents each video as keyframes and temporal motions. These are then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text. At inference, the generated tokens from the LLM are carefully recovered to the original continuous pixel space to create various video content. Our proposed framework is both capable of comprehending and generating image and video content, as demonstrated by its competitive performance across 13 multimodal benchmarks in image and video understanding and generation. Our code and models are available at https://video-lavit.github.io.
Related papers
- TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models [52.590072198551944]
Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents.
For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data.
In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM.
arXiv Detail & Related papers (2024-11-17T13:08:29Z) - Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs.
Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
arXiv Detail & Related papers (2024-10-14T12:35:12Z) - Realizing Video Summarization from the Path of Language-based Semantic Understanding [19.825666473712197]
We propose a novel video summarization framework inspired by the Mixture of Experts (MoE) paradigm.
Our approach integrates multiple VideoLLMs to generate comprehensive and coherent textual summaries.
arXiv Detail & Related papers (2024-10-06T15:03:22Z) - 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) - MEVG: Multi-event Video Generation with Text-to-Video Models [18.06640097064693]
We introduce a novel diffusion-based video generation method, generating a video showing multiple events given multiple individual sentences from the user.
Our method does not require a large-scale video dataset since our method uses a pre-trained text-to-video generative model without a fine-tuning process.
Our proposed method is superior to other video-generative models in terms of temporal coherency of content and semantics.
arXiv Detail & Related papers (2023-12-07T06:53:25Z) - VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools [44.78291853329394]
textbfVidCoM is a fast adaptive framework that leverages Large Language Models (LLMs) to reason about videos using lightweight visual tools.
An InsOVER algorithm locates the corresponding video events based on an efficient Hungarian matching between decompositions of linguistic instructions and video events.
arXiv Detail & Related papers (2023-10-16T17:05:56Z) - Frozen CLIP Models are Efficient Video Learners [86.73871814176795]
Video recognition has been dominated by the end-to-end learning paradigm.
Recent advances in Contrastive Vision-Language Pre-training pave the way for a new route for visual recognition tasks.
We present Efficient Video Learning -- an efficient framework for directly training high-quality video recognition models.
arXiv Detail & Related papers (2022-08-06T17:38:25Z) - End-to-end Generative Pretraining for Multimodal Video Captioning [82.79187814057313]
We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos.
Unlike recent video-language pretraining frameworks, our framework trains both a multimodal video encoder and a sentence decoder jointly.
Our model achieves state-of-the-art performance for multimodal video captioning on four standard benchmarks.
arXiv Detail & Related papers (2022-01-20T16:16:21Z)
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.