Z
Zhe Wang
Researcher at University of California, Irvine
Publications - 36
Citations - 6140
Zhe Wang is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Convolutional neural network & Pose. The author has an hindex of 17, co-authored 35 publications receiving 4419 citations. Previous affiliations of Zhe Wang include Chinese Academy of Sciences & University of California.
Papers
More filters
Book ChapterDOI
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
TL;DR: Temporal Segment Networks (TSN) as discussed by the authors combine a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video, which obtains the state-of-the-art performance on the datasets of HMDB51 and UCF101.
Posted Content
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
TL;DR: Temporal Segment Network (TSN) as discussed by the authors is based on the idea of long-range temporal structure modeling and combines a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video.
Journal ArticleDOI
Temporal Segment Networks for Action Recognition in Videos
TL;DR: Temporal Segment Networks (TSN) as discussed by the authors is proposed to model long-range temporal structure with a new segment-based sampling and aggregation scheme, which enables the TSN framework to efficiently learn action models by using the whole video.
Posted Content
Towards Good Practices for Very Deep Two-Stream ConvNets
TL;DR: This report presents very deep two-stream ConvNets for action recognition, by adapting recent very deep architectures into video domain, and extends the Caffe toolbox into Multi-GPU implementation with high computational efficiency and low memory consumption.
Posted Content
Real-time Action Recognition with Enhanced Motion Vector CNNs
TL;DR: This paper accelerates the deep two-stream architecture by replacing optical flow with motion vector which can be obtained directly from compressed videos without extra calculation, and introduces three strategies for this, initialization transfer, supervision transfer and their combination.