computer-vision-5

Gait Recognition in the Wild

3260 papers • 126 benchmarks • 313 datasets

Gait Recognition in the Wild refers to methods under real-world senses, i.e., unconstrained environment.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in gait-recognition-in-the-wild-5

Trend

Dataset

Best Model

Actions

Gait3D

Libraries

i

Use these libraries to find gait-recognition-in-the-wild-5 models and implementations

Datasets

Gait3D

Subtasks

No subtasks available.

Most implemented papers

Gait Recognition in the Wild with Dense 3D Representations and A Benchmark

Tao Mei, Xinchen Liu, Jinkai Zheng, Wu Liu, Lingxiao He, C. Yan•Tue Apr 05 2022

This paper proposes a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait, and provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics.

212

Content

0

Paper Graph

Gait Recognition in the Wild with Multi-hop Temporal Switch

Chuang Gan, Xinchen Liu, Jinkai Zheng, Wu Liu, C. Yan, Xiaoyan Gu, Yaoqi Sun, Jiyong Zhang•Wed Aug 31 2022

A novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes and achieves high efficiency with fewer model parameters and reduces the difficulty in optimization compared with 3D convolution-based models.

50 0

Paper Graph

Parsing is All You Need for Accurate Gait Recognition in the Wild

Xinchen Liu, Jinkai Zheng, C. Yan, Shuai Wang, Lihao Wang, Wu Liu•Wed Aug 30 2023

The experimental results show a significant improvement in accuracy brought by the GPS representation and the superiority of ParsingGait, the first parsing-based dataset for gait recognition in the wild, by extending the large-scale and challenging Gait3D dataset.

37 0

Paper Graph

LidarGait: Benchmarking 3D Gait Recognition with Point Clouds

Rui Wang, Chao Fan, Chuanfu Shen, Wei Wu, George Q. Huang, Shiqi Yu•Fri Nov 18 2022

The first large-scale LiDAR-based gait recognition dataset, SUSTech1K, is built, which shows that LidarGait outperforms existing point-based and silhouette-based methods by a significant margin, while it also offers stable cross-view results.

86 0

Paper Graph

Adding a benchmark result helps the community track progress.