search

NiyunZhou / The21-dayExpendables

We are the 21-day expandables of a kaggle competition.
Apache License 2.0
15 stars 4 forks source link

ECCV 2016 #7

Open SophieGuan opened 7 years ago

SophieGuan commented 7 years ago

标题含video的文章： Part 2:

  1. Shayan Modiri Assari, Haroon Idrees, and Mubarak Shah. Human Re-identification in Crowd Videos Using Personal, Social and Environmental Constraints 主要讲人群中的人物识别，不太相关
  2. Anita Sellent, Carsten Rother, and Stefan Roth. Stereo Video Deblurring. 主要讲video deblur
  3. Chen Chen, Minh N. Do, and Jue Wang. Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization. 与2相似，video dehazing
  4. Kuo-Hao Zeng, Tseng-Hung Chen, Juan Carlos Niebles, and Min Sun. Title Generation for User Generated Videos. 不太相关，通过设计highlight sensitive captioner和 sentence augmentation两种方式来产生更加准确的video title。不过本篇文章值得借鉴的一点是，在video caption的基础上，它提出先找出一个video的Highlight部分，然后根据highlight进行title的生成。

Part 3:

  1. Zhanpeng Zhang, Ping Luo, Chen Change Loy, and Xiaoou Tang. Joint Face Representation Adaptation and Clustering in Videos. 视频中的人脸聚类
  2. Simone Meyer, Alexander Sorkine-Hornung, and Markus Gro. Phase-Based Modification Transfer for Video. 视频风格迁移
  3. Chuang Gan, Chen Sun, Lixin Duan, and Boqing Gong. Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames. 从互联网获取图像视频数据来辅助视频识别
SophieGuan commented 7 years ago

利用video和temporal两个关键词检索ECCV 2016得到的全部相关文章：

Connectionist Temporal Modeling for Weakly Supervised Action Labeling. De-An Huang, Li Fei-Fei, and Juan Carlos Niebles

Recurrent Temporal Deep Field for Semantic Video Labeling. Peng Lei and Sinisa Todorovic

Video Summarization with Long Short-Term Memory. Ke Zhang

Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video. Yu-Chuan Sun and Kristen Grauman

Temporal Convolutional Networks: A Unified Approach to Action Segmentation

Temporal Segment Networks- Towards Good Practices for Deep Action Recognition

Jian-Fang Hu_Real-Time RGB-D Activity Prediction by Soft Regression