Title | ||
---|---|---|
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Devices |
Abstract | ||
---|---|---|
The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency an... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TPAMI.2020.3029799 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Two dimensional displays,Computational modeling,Three-dimensional displays,Convolution,Streaming media,Training,Solid modeling | Journal | 44 |
Issue | ISSN | Citations |
5 | 0162-8828 | 3 |
PageRank | References | Authors |
0.40 | 21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin, Ji | 1 | 79 | 8.18 |
Chuang Gan | 2 | 253 | 31.92 |
Kuan Wang | 3 | 45 | 3.06 |
Song Han | 4 | 2102 | 79.81 |