InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yi, He, Yinan, Li, Yizhuo, Li, Kunchang, Yu, Jiashuo, Ma, Xin, Li, Xinhao, Chen, Guo, Chen, Xinyuan, Wang, Yaohui, He, Conghui, Luo, Ping, Liu, Ziwei, Wang, Yali, Wang, Limin, Qiao, Yu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914629176786944
author Wang, Yi
He, Yinan
Li, Yizhuo
Li, Kunchang
Yu, Jiashuo
Ma, Xin
Li, Xinhao
Chen, Guo
Chen, Xinyuan
Wang, Yaohui
He, Conghui
Luo, Ping
Liu, Ziwei
Wang, Yali
Wang, Limin
Qiao, Yu
author_facet Wang, Yi
He, Yinan
Li, Yizhuo
Li, Kunchang
Yu, Jiashuo
Ma, Xin
Li, Xinhao
Chen, Guo
Chen, Xinyuan
Wang, Yaohui
He, Conghui
Luo, Ping
Liu, Ziwei
Wang, Yali
Wang, Limin
Qiao, Yu
contents This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words. Our core contribution is to develop a scalable approach to autonomously build a high-quality video-text dataset with large language models (LLM), thereby showcasing its efficacy in learning video-language representation at scale. Specifically, we utilize a multi-scale approach to generate video-related descriptions. Furthermore, we introduce ViCLIP, a video-text representation learning model based on ViT-L. Learned on InternVid via contrastive learning, this model demonstrates leading zero-shot action recognition and competitive video retrieval performance. Beyond basic video understanding tasks like recognition and retrieval, our dataset and model have broad applications. They are particularly beneficial for generating interleaved video-text data for learning a video-centric dialogue system, advancing video-to-text and text-to-video generation research. These proposed resources provide a tool for researchers and practitioners interested in multimodal video understanding and generation.
format Preprint
id arxiv_https___arxiv_org_abs_2307_06942
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
Wang, Yi
He, Yinan
Li, Yizhuo
Li, Kunchang
Yu, Jiashuo
Ma, Xin
Li, Xinhao
Chen, Guo
Chen, Xinyuan
Wang, Yaohui
He, Conghui
Luo, Ping
Liu, Ziwei
Wang, Yali
Wang, Limin
Qiao, Yu
Computer Vision and Pattern Recognition
This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words. Our core contribution is to develop a scalable approach to autonomously build a high-quality video-text dataset with large language models (LLM), thereby showcasing its efficacy in learning video-language representation at scale. Specifically, we utilize a multi-scale approach to generate video-related descriptions. Furthermore, we introduce ViCLIP, a video-text representation learning model based on ViT-L. Learned on InternVid via contrastive learning, this model demonstrates leading zero-shot action recognition and competitive video retrieval performance. Beyond basic video understanding tasks like recognition and retrieval, our dataset and model have broad applications. They are particularly beneficial for generating interleaved video-text data for learning a video-centric dialogue system, advancing video-to-text and text-to-video generation research. These proposed resources provide a tool for researchers and practitioners interested in multimodal video understanding and generation.
title InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.06942