GREW

 News 

August-20-2021: The benchmark toolkit and code will be released at github .

August-18-2021: The benchmark website is online.

July-23-2021: Our GREW paper is accepted by ICCV 2021.

          What is GREW ?
        

The GREW dataset is the first large-scale dataset for gait recognition in the wild.

constructed from natural videos, which contains hundreds of cameras and thousands of hours streams in open systems.

26,345 subjects, 128,671 sequences, 14,185,478 human boxes and a distractor set contains 233,857 sequences.

Silhouettes, Gait Energy Images (GEIs) , optical flow, 2D and 3D poses by automatical processing

Collaborators

Zheng Zhu*

Tsinghua University, XForwardAI Technology

Xianda Guo*

XForwardAI Technology

Tian Yang

XForwardAI Technology

Junjie Huang

XForwardAI Technology

Jiankang Deng

Imperial College London

Guan Huang

XForwardAI Technology

Dalong Du

XForwardAI Technology

Jiwen Lu

Tsinghua University

Jie Zhou

Tsinghua University

            Paper
          

Please cite the following paper if GREW is useful to your research:

              @inproceedings { zhu2021gait,
                title=  {Gait Recognition in the Wild: A Benchmark},
                author=  {Zheng Zhu, Xianda Guo, Tian Yang, Junjie Huang, 
                    Jiankang Deng, Guan Huang, Dalong Du,Jiwen Lu, Jie Zhou},
                booktitle=  {IEEE International Conference on Computer Vision (ICCV)},
                year=  {2021}              
                 }