Global-Local Context Network for Person Search

Global-Local Context Network for Person Search

• Abstract:

​ Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied in the computer vision community over the past few years. In this paper, we delve into the rich context information globally and locally surrounding the target person, which we refer to scene and group context,respectively. Unlike previous works that treat the two types of context individually, we exploit them in a unified global-local context network (GLCNet) with the intuitive aim of feature enhancement. Specifically, re-ID embeddings and context features are enhanced simultaneously in a multi-stage fashion, ultimately leading to enhanced, discriminative features for person search. We conduct the experiments on two person search benchmarks (i.e., CUHK-SYSU and PRW) as well as extend our approach to a more challenging setting (i.e., character search on MovieNet). Extensive experimental results demonstrate the consistent improvement of the proposed GLCNet over the state-of-the-art methods on the three datasets.

• Overall architecture of our GLCNet:

Performance

• Different gallery size on CUHK-SYSU:

• Qualitative Results:

  

Train

sh ./run_${DATASET}.sh

Test

sh ./test_${DATASET}.sh

Inference

Run the demo.py to make inference on given images. GLCNet runs at 10.3 fps on a single Tesla V100 GPU with batch_size 3.

MovieNet-CS

To extend person search framework to a more challenging task, i.e., character search (CS). We borrow the character detection and ID annotations from the MovieNet dataset to organize MovieNet-CS, and set different levels of training set and different gallery size same as CUHK-SYSU. MovieNet-CS is saved exactly the same format and structure as CUHK-SYSU, which could be of great convenience to further research and experiments. If you want to use MovieNet-CS, please download movie frames on the official website of MovieNet and our reorganized annotations here(TBD).

Acknowledgement

Thanks to the solid codebase from SeqNet.

Citation

@ARTICLE{2021arXiv211202500Z,
    author   = {Peng Zheng and
                Jie Qin and
                Yichao Yan and
                Shengcai Liao and
                Bingbing Ni and
                Xiaogang Cheng and
                Ling Shao},
    title    = {Global-Local Context Network for Person Search},
    journal  = {arXiv e-prints},
    volume   = {abs/2109.00211},
    year     = {2021}
}