Gait3D is a large-scale 3D representation-based gait recognition dataset. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene.
Variants: Gait3D
This dataset is used in 1 benchmark:
Task | Model | Paper | Date |
---|---|---|---|
Gait Recognition | HSTL | Hierarchical Spatio-Temporal Representation Learning for … | 2023-07-19 |
Gait Recognition | SMPLGait | Gait Recognition in the Wild … | 2022-04-06 |
Recent papers with results on this dataset: