Di Chen

Personal Information

Publications

2022

Conference paper

A. Doering, D. Chen, S. Zhang, B. Schiele, and J. Gall

“PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.

mehr

BibTeX

@inproceedings{Doering_CVPR22,
TITLE = {{PoseTrack21}: {A} Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking},
AUTHOR = {Doering, Andreas and Chen, Di and Zhang, Shanshan and Schiele, Bernt and Gall, J{\"u}rgen},
LANGUAGE = {eng},
ISBN = {978-1-6654-6946-3},
DOI = {10.1109/CVPR52688.2022.02029},
PUBLISHER = {IEEE},
YEAR = {2022},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)},
PAGES = {20931--20940},
ADDRESS = {New Orleans, LA, USA},
}

Endnote

%0 Conference Proceedings
%A Doering, Andreas
%A Chen, Di
%A Zhang, Shanshan
%A Schiele, Bernt
%A Gall, J&#252;rgen
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
%T PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-183B-8
%R 10.1109/CVPR52688.2022.02029
%D 2022
%B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition
%Z date of event: 2022-06-19 - 2022-06-24
%C New Orleans, LA, USA
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%P 20931 - 20940
%I IEEE
%@ 978-1-6654-6946-3

Conference paper

D. Chen, A. Doering, S. Zhang, J. Yang, J. Gall, and B. Schiele

“Keypoint Message Passing for Video-Based Person Re-identification,” in Proceedings of the 36th AAAI Conference on Artificial Intelligence, Virtual Conference, 2022.

mehr

BibTeX

@inproceedings{ChenAAAI22,
TITLE = {Keypoint Message Passing for Video-Based Person Re-identification},
AUTHOR = {Chen, Di and Doering, Andreas and Zhang, Shanshan and Yang, Jian and Gall, Juergen and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-57735-876-3},
DOI = {10.1609/aaai.v36i1.19899},
PUBLISHER = {AAAI},
YEAR = {2022},
BOOKTITLE = {Proceedings of the 36th AAAI Conference on Artificial Intelligence},
PAGES = {239--247},
ADDRESS = {Virtual Conference},
}

Endnote

%0 Conference Proceedings
%A Chen, Di
%A Doering, Andreas
%A Zhang, Shanshan
%A Yang, Jian
%A Gall, Juergen
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Keypoint Message Passing for Video-Based Person Re-identification  : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-182F-6
%R 10.1609/aaai.v36i1.19899 
%D 2022
%B 36th AAAI Conference on Artificial Intelligence
%Z date of event: 2022-02-22 - 2022-03-01
%C Virtual Conference
%B Proceedings of the 36th AAAI Conference on Artificial Intelligence
%P 239 - 247
%I AAAI
%@ 978-1-57735-876-3
%U https://ojs.aaai.org/index.php/AAAI/article/view/19899

2021

Article

D. Chen, S. Zhang, J. Yang, and B. Schiele

“Norm-Aware Embedding for Efficient Person Search and Tracking,” International Journal of Computer Vision, vol. 129, 2021.

mehr

BibTeX

@article{Chen2021,
TITLE = {Norm-Aware Embedding for Efficient Person Search and Tracking},
AUTHOR = {Chen, Di and Zhang, Shanshan and Yang, Jian and Schiele, Bernt},
LANGUAGE = {eng},
ISSN = {0920-5691},
DOI = {10.1007/s11263-021-01512-5},
PUBLISHER = {Springer},
ADDRESS = {New York, NY},
YEAR = {2021},
DATE = {2021},
JOURNAL = {International Journal of Computer Vision},
VOLUME = {129},
PAGES = {3154--3168},
}

Endnote

%0 Journal Article
%A Chen, Di
%A Zhang, Shanshan
%A Yang, Jian
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Norm-Aware Embedding for Efficient Person Search and Tracking : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0009-6169-4
%R 10.1007/s11263-021-01512-5
%7 2021
%D 2021
%J International Journal of Computer Vision
%O Int. J. Comput. Vis.
%V 129
%& 3154
%P 3154 - 3168
%I Springer
%C New York, NY
%@ false

2020

Conference paper

D. Chen, S. Zhang, W. Ouyang, J. Yang, and B. Schiele

“Hierarchical Online Instance Matching for Person Search,” in AAAI Technical Track: Vision, New York, NY, USA, 2020.

mehr

BibTeX

@inproceedings{Chen_aaai20,
TITLE = {Hierarchical Online Instance Matching for Person Search},
AUTHOR = {Chen, Di and Zhang, Shanshan and Ouyang, Wanli and Yang, Jian and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-57735-835-0},
DOI = {10.1609/aaai.v34i07.6623},
PUBLISHER = {AAAI},
YEAR = {2020},
DATE = {2020},
BOOKTITLE = {AAAI Technical Track: Vision},
PAGES = {1518--1525},
ADDRESS = {New York, NY, USA},
}

Endnote

%0 Conference Proceedings
%A Chen, Di
%A Zhang, Shanshan
%A Ouyang, Wanli
%A Yang, Jian
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Hierarchical Online Instance Matching for Person Search : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0005-EB78-C
%R 10.1609/aaai.v34i07.6623
%D 2020
%B Thirty-Fourth AAAI Conference on Artificial Intelligence
%Z date of event: 2020-02-07 - 2020-02-12
%C New York, NY, USA
%B AAAI Technical Track: Vision
%P 1518 - 1525
%I AAAI
%@ 978-1-57735-835-0

Conference paper

D. Chen, S. Zhang, J. Yang, and B. Schiele

“Norm-Aware Embedding for Efficient Person Search,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA, USA (Virtual), 2020.

mehr

BibTeX

@inproceedings{chen2020nae,
TITLE = {Norm-Aware Embedding for Efficient Person Search},
AUTHOR = {Chen, Di and Zhang, Shanshan and Yang, Jian and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-7281-7168-5},
DOI = {10.1109/CVPR42600.2020.01263},
PUBLISHER = {IEEE},
YEAR = {2020},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)},
PAGES = {12612--12621},
ADDRESS = {Seattle, WA, USA (Virtual)},
}

Endnote

%0 Conference Proceedings
%A Chen, Di
%A Zhang, Shanshan
%A Yang, Jian
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Norm-Aware Embedding for Efficient Person Search : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0005-EB86-B
%R 10.1109/CVPR42600.2020.01263
%D 2020
%B 33rd IEEE Conference on Computer Vision and Pattern Recognition
%Z date of event: 2020-06-14 - 2020-06-19
%C Seattle, WA, USA (Virtual)
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%P 12612 - 12621
%I IEEE
%@ 978-1-7281-7168-5

Paper

A. Doering, D. Chen, S. Zhang, B. Schiele, and J. Gall

“PoseTrackReID: Dataset Description,” 2020. [Online]. Available: https://arxiv.org/abs/2011.06243.

mehr

Abstract

Current datasets for video-based person re-identification (re-ID) do not
include structural knowledge in form of human pose annotations for the persons
of interest. Nonetheless, pose information is very helpful to disentangle
useful feature information from background or occlusion noise. Especially
real-world scenarios, such as surveillance, contain a lot of occlusions in
human crowds or by obstacles. On the other hand, video-based person re-ID can
benefit other tasks such as multi-person pose tracking in terms of robust
feature matching. For that reason, we present PoseTrackReID, a large-scale
dataset for multi-person pose tracking and video-based person re-ID. With
PoseTrackReID, we want to bridge the gap between person re-ID and multi-person
pose tracking. Additionally, this dataset provides a good benchmark for current
state-of-the-art methods on multi-frame person re-ID.

BibTeX

@online{Doering_arXiv2011.06243,
TITLE = {{PoseTrackReID}: {D}ataset Description},
AUTHOR = {Doering, Andreas and Chen, Di and Zhang, Shanshan and Schiele, Bernt and Gall, Juergen},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2011.06243},
EPRINT = {2011.06243},
EPRINTTYPE = {arXiv},
YEAR = {2020},
ABSTRACT = {Current datasets for video-based person re-identification (re-ID) do not<br>include structural knowledge in form of human pose annotations for the persons<br>of interest. Nonetheless, pose information is very helpful to disentangle<br>useful feature information from background or occlusion noise. Especially<br>real-world scenarios, such as surveillance, contain a lot of occlusions in<br>human crowds or by obstacles. On the other hand, video-based person re-ID can<br>benefit other tasks such as multi-person pose tracking in terms of robust<br>feature matching. For that reason, we present PoseTrackReID, a large-scale<br>dataset for multi-person pose tracking and video-based person re-ID. With<br>PoseTrackReID, we want to bridge the gap between person re-ID and multi-person<br>pose tracking. Additionally, this dataset provides a good benchmark for current<br>state-of-the-art methods on multi-frame person re-ID.<br>},
}

Endnote

%0 Report
%A Doering, Andreas
%A Chen, Di
%A Zhang, Shanshan
%A Schiele, Bernt
%A Gall, Juergen
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
%T PoseTrackReID: Dataset Description : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0007-80FA-E
%U https://arxiv.org/abs/2011.06243
%D 2020
%X   Current datasets for video-based person re-identification (re-ID) do not<br>include structural knowledge in form of human pose annotations for the persons<br>of interest. Nonetheless, pose information is very helpful to disentangle<br>useful feature information from background or occlusion noise. Especially<br>real-world scenarios, such as surveillance, contain a lot of occlusions in<br>human crowds or by obstacles. On the other hand, video-based person re-ID can<br>benefit other tasks such as multi-person pose tracking in terms of robust<br>feature matching. For that reason, we present PoseTrackReID, a large-scale<br>dataset for multi-person pose tracking and video-based person re-ID. With<br>PoseTrackReID, we want to bridge the gap between person re-ID and multi-person<br>pose tracking. Additionally, this dataset provides a good benchmark for current<br>state-of-the-art methods on multi-frame person re-ID.<br>
%K Computer Science, Computer Vision and Pattern Recognition, cs.CV