本文详述了Temporal Shift Module (TSM)在行为识别中的应用，它能以2D CNN的复杂度达到3D CNN的效果。TSM通过通道内的时间转移实现效率提升，对比了与其他方法如TSN、TRN、ECO和Non-local I3D + GCN的优缺点，并展示了在Something-Something-V1数据集上的优秀表现。
行为识别论文笔记|TSM|TSM: Temporal Shift Module for Efficient Video Understanding
Lin, Ji , C. Gan , and S. Han . “TSM: Temporal Shift Module for Efficient Video Understanding.” 2019 IEEE/CVF International Conference on Computer Vision (ICCV) IEEE, 2019.
Contents
Motivations
-
Temporal Shift Module (TSM) can achieve the performance of 3D CNN but maintain 2D CNN’s complexity.
-
Address shift, which is a hardware-friendly primitive, has also been exploited for compact 2D CNN design on image recognition tasks
Chen, Weijie, et al. “All you need is a few shifts: Designing efficient convolutional neural networks for image classification.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.
Wu, Bichen, et al. “Shift: A zero flop, zero parameter alternative to spatial convolutions.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
He, Yihui, et al. “Addressnet: Shift-based primitives for efficient convolutional neural networks.” 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019.
最低0.47元/天 解锁文章
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
