CVPR2016 有哪些值得关注的文章,求推荐!

已邀请:
我把Action Recognition相关的论文列在这里,最近在刷paper,有空再补充
0. Learning Action Maps of Large Environments via First-Person Vision.
   通过第一人称视角视频理解场景中的“功能性地图”
1. Progressively Parsing Interactional Objects for Fine Grained Action Detection. 
2. Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs. 
3. What If We Do Not Have Multiple Videos of the Same Action? — Video Action Localization Using Web Images. 
4. 3D Action Recognition From Novel Viewpoints.
5. Convolutional Two-Stream Network Fusion for Video Action Recognition.
    专门研究Two-stream中的融合方法,并给出了三个实验结论:卷积层融合相比分类层融合不会损失多少精度,但可以减少参数;晚融合比早融合要好,分类层融合可以提高精度;在时空领域上做特征图pooling可以提高性能。
6. VLAD3: Encoding Dynamics of Deep Features for Action Recognition. 
7. A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection.
    使用multi-stream CNN和双向LSTM来提取动作表示,并且利用跟踪器来定位人,抑制背景噪声。
8. A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets. 
9. A Key Volume Mining Deep Framework for Action Recognition. 
    提取视频中的关键卷,在关键卷的基础上进行动作识别。
10. First Person Action Recognition Using Deep Learned Descriptors. 
11. Mining 3D Key-Pose-Motifs for Action Recognition. 
12. Predicting the Where and What of Actors and Actions Through Online Action Localization.
13. End-To-End Learning of Action Detection From Frame Glimpses in Videos. 
14. Action Recognition in Video Using Sparse Coding and Relative Features. 
15. Improving Human Action Recognition by Non-Action Classification.
16. Real-Time Action Recognition With Enhanced Motion Vector CNNs. 
17. Dynamic Image Networks for Action Recognition.
      提出了一种新颖的视频表示。
18. Regularizing Long Short Term Memory With 3D Human-Skeleton Sequences for Action Recognition. 
19. Temporal Action Localization With Pyramid of Score Distribution Features. 
20. Temporal Action Detection Using a Statistical Language Model. 
      时域动作检测,从视频中自动定位和分类动作片段,通过语言模型表示时域和上下文结构。
21. Deep Region and Multi-Label Learning for Facial Action Unit Detection. 
22. Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection.
23. DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns. 
24. Copula Ordinal Regression for Joint Estimation of Facial Action Unit Intensity. 

南七骄傲 - 90后IT男

赞同来自:

这个还是得看你做的方向吧

要回复问题请先登录注册