Deep Feature Flow for Video Recognition
Deep Feature Flow for Video Recognition
复制标题
DOI：
10.1109/cvpr.2017.441
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Xizhou Zhu;Yuwen Xiong;Jifeng Dai;Lu Yuan;Yichen Wei
中科院分区：
文献类型：
--
作者：
Xizhou Zhu;Yuwen Xiong;Jifeng Dai;Lu Yuan;Yichen Wei
深度卷积神经网络在图像识别任务上取得了巨大成功。然而，将最先进的图像识别网络转移到视频中并非易事，因为每帧评估太慢且负担不起。我们提出了深度特征流，这是一个快速准确的视频识别框架。它仅在稀疏关键帧上运行昂贵的卷积子网络，并通过流场将其深度特征映射传播到其他帧。它实现了显着的加速，因为流计算相对较快。整个架构的端到端训练显著提高了识别准确率。深度特征流具有灵活性和通用性。在最近的两个大规模视频数据集上进行了验证。它向实用的视频识别迈出了一大步。代码将被释放。
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.