InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding
arxiv(2024)
摘要
We introduce InternVideo2, a new video foundation model (ViFM) that achieves
the state-of-the-art performance in action recognition, video-text tasks, and
video-centric dialogue. Our approach employs a progressive training paradigm
that unifies the different self- or weakly-supervised learning frameworks of
masked video token reconstruction, cross-modal contrastive learning, and next
token prediction. Different training stages would guide our model to capture
different levels of structure and semantic information through different
pretext tasks. At the data level, we prioritize the spatiotemporal consistency
by semantically segmenting videos and generating video-audio-speech captions.
This improves the alignment between video and text. We scale both data and
model size for our InternVideo2. Through extensive experiments, we validate our
designs and demonstrate the state-of-the-art performance on over 60 video and
audio tasks. Notably, our model outperforms others on various video-related
captioning, dialogue, and long video understanding benchmarks, highlighting its
ability to reason and comprehend long temporal contexts. Code and models are
available at https://github.com/OpenGVLab/InternVideo2/.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要