2022
Cao, Jiale; Pang, Yenwai; Anwer, Rao Muhammad; Cholakkal, Hisham; Xie, Jin; Shah, Mubarak; Khan, Fahad Shahbaz
PSTR: End-to-End One-Step Person Search With Transformers Conference
IEEE Computer Vision and Pattern Recognition, 2022.
Abstract | Tags: CVPR, Re-Identification, Transformers, Visual Search | Links:
@conference{nokey_108,
title = {PSTR: End-to-End One-Step Person Search With Transformers},
author = {Jiale Cao and Yenwai Pang and Rao Muhammad Anwer and Hisham Cholakkal and Jin Xie and Mubarak Shah and Fahad Shahbaz Khan},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/05237-2.pdf
https://github.com/JialeCao001/PSTR},
year = {2022},
date = {2022-06-19},
urldate = {2022-06-19},
publisher = {IEEE Computer Vision and Pattern Recognition},
abstract = {We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.},
keywords = {CVPR, Re-Identification, Transformers, Visual Search},
pubstate = {published},
tppubtype = {conference}
}
We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.
Cao, Jiale; Pang, Yenwai; Anwer, Rao Muhammad; Cholakkal, Hisham; Xie, Jin; Shah, Mubarak; Khan, Fahad Shahbaz
PSTR: End-to-End One-Step Person Search With Transformers Conference
IEEE Computer Vision and Pattern Recognition, 2022.
Abstract | Tags: CVPR, Re-Identification, Transformers, Visual Search | Links:
@conference{nokey_156,
title = {PSTR: End-to-End One-Step Person Search With Transformers},
author = {Jiale Cao and Yenwai Pang and Rao Muhammad Anwer and Hisham Cholakkal and Jin Xie and Mubarak Shah and Fahad Shahbaz Khan},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/05237-2.pdf
https://github.com/JialeCao001/PSTR},
year = {2022},
date = {2022-06-19},
urldate = {2022-06-19},
publisher = {IEEE Computer Vision and Pattern Recognition},
abstract = {We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.},
keywords = {CVPR, Re-Identification, Transformers, Visual Search},
pubstate = {published},
tppubtype = {conference}
}
We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.
discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step
transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging
PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.
2019
Alemu, Leulseged Tesfaye; Pelillo, Marcello; Shah, Mubarak
Deep Constrained Dominant Sets for Person Re-Identification Conference
International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2, 2019.
Tags: Re-Identification | Links:
@conference{Alemu2019,
title = {Deep Constrained Dominant Sets for Person Re-Identification},
author = {Leulseged Tesfaye Alemu and Marcello Pelillo and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2019/08/Publications_Deep-Constrained-Dominant-Sets-for-Person-Re-Identification.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2019/08/Publications_Deep-Constrained-Dominant-Sets-for-Person-Re-Identification_Supplementary.pdf
https://www.crcv.ucf.edu/research/projects/deep-constrained-dominant-sets-for-person-re-identification/},
year = {2019},
date = {2019-10-28},
publisher = {International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2},
keywords = {Re-Identification},
pubstate = {published},
tppubtype = {conference}
}
Alemu, Leulseged Tesfaye; Pelillo, Marcello; Shah, Mubarak
Deep Constrained Dominant Sets for Person Re-Identification Conference
International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2, 2019.
Tags: Re-Identification | Links:
@conference{Alemu2019b,
title = {Deep Constrained Dominant Sets for Person Re-Identification},
author = {Leulseged Tesfaye Alemu and Marcello Pelillo and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2019/08/Publications_Deep-Constrained-Dominant-Sets-for-Person-Re-Identification.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2019/08/Publications_Deep-Constrained-Dominant-Sets-for-Person-Re-Identification_Supplementary.pdf
https://www.crcv.ucf.edu/research/projects/deep-constrained-dominant-sets-for-person-re-identification/},
year = {2019},
date = {2019-10-28},
publisher = {International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2},
keywords = {Re-Identification},
pubstate = {published},
tppubtype = {conference}
}
2018
Kalayeh, Mahdi M.; Basaran, Emrah; Gokmen, Muhittin; Kamasak, Mustafa E.; Shah, Mubarak
Human Semantic Parsing for Person Re-identification Conference
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, June 18-22, 2018, 2018.
Tags: Re-Identification | Links:
@conference{Kalayeh2018,
title = {Human Semantic Parsing for Person Re-identification},
author = {Mahdi M. Kalayeh and Emrah Basaran and Muhittin Gokmen and Mustafa E. Kamasak and Mubarak Shah},
url = {http://openaccess.thecvf.com/content_cvpr_2018/papers/Kalayeh_Human_Semantic_Parsing_CVPR_2018_paper.pdf
https://www.crcv.ucf.edu/papers/cvpr2018/semantic_parsing.tex},
year = {2018},
date = {2018-03-31},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, June 18-22, 2018},
keywords = {Re-Identification},
pubstate = {published},
tppubtype = {conference}
}
Kalayeh, Mahdi M.; Basaran, Emrah; Gokmen, Muhittin; Kamasak, Mustafa E.; Shah, Mubarak
Human Semantic Parsing for Person Re-identification Conference
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, June 18-22, 2018, 2018.
Tags: Re-Identification | Links:
@conference{Kalayeh2018b,
title = {Human Semantic Parsing for Person Re-identification},
author = {Mahdi M. Kalayeh and Emrah Basaran and Muhittin Gokmen and Mustafa E. Kamasak and Mubarak Shah},
url = {http://openaccess.thecvf.com/content_cvpr_2018/papers/Kalayeh_Human_Semantic_Parsing_CVPR_2018_paper.pdf
https://www.crcv.ucf.edu/papers/cvpr2018/semantic_parsing.tex},
year = {2018},
date = {2018-03-31},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, June 18-22, 2018},
keywords = {Re-Identification},
pubstate = {published},
tppubtype = {conference}
}