We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that unifies the masked video modeling, crossmodal contrastive learning, and next token prediction, scaling up the video encoder size to 6B parameters. At the data level, we prioritize spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. Through extensive experiments, we validate our designs and demonstrate superior performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related dialogue and long video understanding benchmarks, highlighting its ability to reason and comprehend longer contexts. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2/.
@article{arxiv.2403.15377,
title = {InternVideo2: Scaling Foundation Models for Multimodal Video Understanding},
author = {Yi Wang and Kunchang Li and Xinhao Li and Jiashuo Yu and Yinan He and Chenting Wang and Guo Chen and Baoqi Pei and Ziang Yan and Rongkun Zheng and Jilan Xu and Zun Wang and Yansong Shi and Tianxiang Jiang and Songze Li and Hongjie Zhang and Yifei Huang and Yu Qiao and Yali Wang and Limin Wang},
journal= {arXiv preprint arXiv:2403.15377},
year = {2024}
}
Comments
a technical report about video understanding (accepted to ECCV2024)