Deep Feature Flow for Video Recognition

Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, Yichen Wei; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2349-2358


Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable. We present deep feature flow, a fast and accurate framework for video recognition. It runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field. It achieves significant speedup as flow computation is relatively fast. The end-to-end training of the whole architecture significantly boosts the recognition accuracy. Deep feature flow is flexible and general. It is validated on two recent large scale video datasets. It makes a large step towards practical video recognition. Code would be released.

Related Material

[pdf] [arXiv]
author = {Zhu, Xizhou and Xiong, Yuwen and Dai, Jifeng and Yuan, Lu and Wei, Yichen},
title = {Deep Feature Flow for Video Recognition},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}