Pedestrian Attribute
The PEdesTrian Attribute dataset (PETA) is a dataset fore recognizing pedestrian attributes, such as gender and clothing style, at a far distance. It is of interest in video surveillance scenarios where face and body close-shots and hardly available. It consists of 19,000 pedestrian images with 65 attributes (61 binary and 4 multi-class). Those images contain 8705 persons.
Source: Attribute Aware Pooling for Pedestrian Attribute Recognition
Image Source: http://mmlab.ie.cuhk.edu.hk/projects/PETA.html
Variants: PETA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Pedestrian Attribute Recognition | UniHCP (FT) | UniHCP: A Unified Model for … | 2023-03-06 |
| Pedestrian Attribute Recognition | ALM[tang2019Improving] (ICCV19) | Rethinking of Pedestrian Attribute Recognition: … | 2020-05-25 |
| Pedestrian Attribute Recognition | strongbaseline | Rethinking of Pedestrian Attribute Recognition: … | 2020-05-25 |
| Pedestrian Attribute Recognition | Attribute-Specific Localization | Improving Pedestrian Attribute Recognition With … | 2019-10-10 |
| Pedestrian Attribute Recognition | HP-net | HydraPlus-Net: Attentive Deep Features for … | 2017-09-28 |
Recent papers with results on this dataset: