English

Streaming Video Model

Computer Vision and Pattern Recognition 2023-03-31 v1

Abstract

Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract spatiotemporal features, while frame-based video tasks, such as multiple object tracking (MOT), rely on single fixed-image backbone to extract spatial features. In contrast, we propose to unify video understanding tasks into one novel streaming video architecture, referred to as Streaming Vision Transformer (S-ViT). S-ViT first produces frame-level features with a memory-enabled temporally-aware spatial encoder to serve the frame-based video tasks. Then the frame features are input into a task-related temporal decoder to obtain spatiotemporal features for sequence-based tasks. The efficiency and efficacy of S-ViT is demonstrated by the state-of-the-art accuracy in the sequence-based action recognition task and the competitive advantage over conventional architecture in the frame-based MOT task. We believe that the concept of streaming video model and the implementation of S-ViT are solid steps towards a unified deep learning architecture for video understanding. Code will be available at https://github.com/yuzhms/Streaming-Video-Model.

Keywords

Cite

@article{arxiv.2303.17228,
  title  = {Streaming Video Model},
  author = {Yucheng Zhao and Chong Luo and Chuanxin Tang and Dongdong Chen and Noel Codella and Zheng-Jun Zha},
  journal= {arXiv preprint arXiv:2303.17228},
  year   = {2023}
}

Comments

Accepted by CVPR'23

R2 v1 2026-06-28T09:41:00.496Z