TEINet: Towards an Efficient Architecture for Video Recognition(AAAI2020)
AAAI2020 南京大學+騰訊優圖實驗室 1 摘要 在視頻動作識別的架構設計中，效率是一個重要的問題。3D CNNs在視頻動作識別方面取得了顯著的進展。然而，與二維卷積相比，三維卷積往往引入大量的參數，導致計算量大。爲了解決這個問題，我們提出了一個有效的時序模塊，稱爲Temporal Enhancement-and-Interaction（TEI模塊），它可以插入到現有的2D CNNs中。TEI
相關文章
- 1. 論文瀏覽(22) TEINet: Towards an Efficient Architecture for Video Recognition
- 2. Video Architecture Search
- 3. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- 4. 6 Multi-Cloud Architecture Designs for an Effective Cloud
- 5. Path-Level Network Transformation for Efficient Architecture Search
- 6. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- 7. Paper Reading：ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- 8. Flash: An Efficient and Portable Web Server
- 9. Spatially Adaptive Residual Networks for Efficient Image and Video Deblurring
- 10. ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • RxJava操作符（一）Creating Observables
- • PHP開發工具
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 論文瀏覽(22) TEINet: Towards an Efficient Architecture for Video Recognition
- 2. Video Architecture Search
- 3. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- 4. 6 Multi-Cloud Architecture Designs for an Effective Cloud
- 5. Path-Level Network Transformation for Efficient Architecture Search
- 6. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- 7. Paper Reading：ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- 8. Flash: An Efficient and Portable Web Server
- 9. Spatially Adaptive Residual Networks for Efficient Image and Video Deblurring
- 10. ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications