ICCV 2017 UCT:《UCT: Learning Unified Convolutional Networks forReal-time Visual Tracking》論文筆記
理解出錯之處望不吝指正。 本文模型叫做UCT。就像論文題目一樣，作者提出了一個基於卷積神經網絡的end2end的tracking模型。模型的整體結構如下圖所示（圖中實線代表online tracking過程，虛線框內和虛線表示離線訓練過程和在第一幀進行訓練）： 模型的目的是從樣本中學習出一系列convolution filter ，則在樣本上進行卷積得到的卷積response爲
相關文章
- 1. ICCV 2017 CREST：《CREST: Convolutional Residual Learning for Visual Tracking》論文筆記
- 2. ICCV 2017 DSiam:《Learning Dynamic Siamese Network for Visual Object Tracking》論文筆記
- 3. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 論文筆記
- 4. ICCV 2017 EAST:《Learning Policies for Adaptive Tracking with Deep Feature Cascades》論文筆記
- 5. 論文閱讀：MDNet: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 6. CREST: Convolutional Residual Learning for Visual Tracking
- 7. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 8. MDNet: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 9. VITAL: VIsual Tracking via Adversarial Learning論文筆記
- 10. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 閱讀筆記
- 更多相關文章...
- • ASP.NET Razor - 標記 - ASP.NET 教程
- • CAP理論是什麼？ - NoSQL教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • Scala 中文亂碼解決
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. ICCV 2017 CREST：《CREST: Convolutional Residual Learning for Visual Tracking》論文筆記
- 2. ICCV 2017 DSiam:《Learning Dynamic Siamese Network for Visual Object Tracking》論文筆記
- 3. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 論文筆記
- 4. ICCV 2017 EAST:《Learning Policies for Adaptive Tracking with Deep Feature Cascades》論文筆記
- 5. 論文閱讀：MDNet: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 6. CREST: Convolutional Residual Learning for Visual Tracking
- 7. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 8. MDNet: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- 9. VITAL: VIsual Tracking via Adversarial Learning論文筆記
- 10. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 閱讀筆記