ShuangLI59/person_search
Joint Detection and Identification Feature Learning for Person Search
Built on a customized Caffe framework with multi-GPU support and memory optimization, this implementation combines Faster R-CNN-based detection with metric learning for simultaneous person localization and re-identification. The architecture leverages ResNet-50 features and supports distributed training via MPI, enabling evaluation across multiple GPUs for efficient ranking-based person search with mAP and top-k metrics.
755 stars. No commits in the last 6 months.
Stars
755
Forks
240
Language
Python
License
—
Category
Last pushed
Apr 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ShuangLI59/person_search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
VlSomers/bpbreid
[WACV23] A strong baseline for body part-based person re-identification
VlSomers/keypoint_promptable_reidentification
[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and...
skylab-tech/ffhqr-dataset
FFHQR -- the first large-scale retouching dataset for computer vision research.
layumi/Vehicle_reID-Collection
:red_car: the collection of vehicle re-ID papers, datasets. :red_car:
badalyaz/object-re-identification
Person Re-Identification (ReID) using lightweight Deep Learning model.