Cross-Camera Feature Prediction (CCFP)
The official implementation for the Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes which is accepted by ACMMM-2021.
Environment
The code is based on fastreid. See INSTALL.md.
For Compiling with cython to accelerate evalution
cd fastreid/evaluation/rank_cylib; make all
Dataset Preparation
- Download Market-1501 and DukeMTMC-reID
- Split Market-1501 and DukeMTMC-reID to Market-sct and DukeMTMC-sct according to the file names in the market_sct.txt and duke_sct.txt
vim fastreid/data/build.py
change the_root
to your own data folder- Make new directories in data and organize them as follows:
+-- data | +-- market | +-- market_sct | +-- query | +-- boudning_box_test | +-- duke | +-- duke_sct | +-- query | +-- boudning_box_test
Train and test
To train market-sct with CCFP, simply run
sh run.sh
To train duke-sct with CCFP, simply run
sh run_d.sh
Experiments
Citation
If you find this code useful, please kindly cite the following paper:
@inproceedings{ge2021cross, title={Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes}, author={Ge, Wenhang and Pan, Chunyan and Wu, Ancong and Zheng, Hongwei and Zheng, Wei-Shi}, booktitle={Proceedings of the 29th ACM International Conference on Multimedia}, pages={3644--3653}, year={2021} }