PyTorch person re-identification models, scripts, pretrained weights
-
Updated
Apr 17, 2023 - Python
PyTorch person re-identification models, scripts, pretrained weights
Beyond strong basleine for Person Re-ID. 2019
CUHK03 extracted images from the .mat file
A New Strong and Simple Baseline Method for VI-ReID (Bridging the Gap: Multi-level Cross-modality Joint Alignment for Visible-infrared Person Re-identification)
LOMO Feature extraction for PRID. Contains extracted features of PRID450S dataset.
Multi-Tracking Multi-Camera Person Re-Identification
Code for paper: "Query-based Universal Adversarial Perturbation for Person Re-Identification Attack" (PRCV2022)
A professionally curated list of resources (paper, code, data, etc.) on 3D Skeleton Based Person Re-ID.
The deep person re-id implementation based on Caffe
A Part Power Set Model for Scale-Free Person Retrieval
Repo for BMVC2020 paper "BCaR: Beginner Classifier as Regularization Towards Generalizable Re-ID"
An implementation of the person re-identification
This repository provides the X-MARS dataset splits for image to video/tracklet evaluation.
[NeurIPS 2021] TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification
CMLD: Contrastive mutual learning distillation for unsupervised domain adaptive person re-identification
Person Re-identification by Local Maximal Occurrence Representation and Metric Learning
Temporal Lifting (TLift), a model-free temporal cooccurrence based score weighting method proposed in "Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting".
ICCV 2023, project page of the paper "DeepChange: A Long-term Person Re-identification Benchmark"
Video-based Person Re-identification without Bells and Whistles (CVPRw 2021)
Add a description, image, and links to the person-re-identification topic page so that developers can more easily learn about it.
To associate your repository with the person-re-identification topic, visit your repo's landing page and select "manage topics."