The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
개인 재식별(Re-ID)은 다양한 카메라 뷰에서 동일한 보행자 신원 이미지를 일치시키는 것을 목표로 합니다. 보행자는 상대적으로 오랜 시간 동안 자주 옷을 갈아입기 때문에 현재의 많은 방법은 색상 외관 정보에 크게 의존하거나 사람의 생체 특징에만 초점을 맞추는 반면 이러한 방법은 옷 갈아입기에 적용할 때 성능이 명백히 저하됩니다. 이러한 딜레마를 해소하기 위해 우리는 세분화된 로컬 특징을 학습하는 새로운 Multi Feature Fusion Attention Network(MFFAN)을 제안했습니다. 그런 다음 모델이 보행자의 생체 인식 기능을 학습하도록 안내하기 위해 여러 세분성 기능을 통합할 수 있는 CAA(Clothing Adaptive Attention) 모듈을 도입했습니다. 한편, 옷을 바꾸는 Re-ID 문제에 대한 우리 방법의 성능을 완전히 검증하기 위해 서로 다른 옷을 입은 동일한 신원의 여러 사진을 생성할 수 있는 CGN(Clothing Generation Network)을 설계했습니다. 마지막으로, 실험 결과는 우리의 방법이 VCcloth 및 PRCC 데이터 세트에서 각각 5% 및 6% 이상 현재 최상의 방법을 초과한다는 것을 보여줍니다.
Liwei WANG
Wuhan Institute of Technology
Yanduo ZHANG
Wuhan Institute of Technology
Tao LU
Wuhan Institute of Technology
Wenhua FANG
Wuhan Institute of Technology
Yu WANG
Wuhan Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Liwei WANG, Yanduo ZHANG, Tao LU, Wenhua FANG, Yu WANG, "Multi Feature Fusion Attention Learning for Clothing-Changing Person Re-Identification" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 8, pp. 1170-1174, August 2022, doi: 10.1587/transfun.2021EAL2097.
Abstract: Person re-identification (Re-ID) aims to match the same pedestrain identity images across different camera views. Because pedestrians will change clothes frequently for a relatively long time, while many current methods rely heavily on color appearance information or only focus on the person biometric features, these methods make the performance dropped apparently when it is applied to Clohting-Changing. To relieve this dilemma, we proposed a novel Multi Feature Fusion Attention Network (MFFAN), which learns the fine-grained local features. Then we introduced a Clothing Adaptive Attention (CAA) module, which can integrate multiple granularity features to guide model to learn pedestrain's biometric feature. Meanwhile, in order to fully verify the performance of our method on clothing-changing Re-ID problem, we designed a Clothing Generation Network (CGN), which can generate multiple pictures of the same identity wearing different clothes. Finally, experimental results show that our method exceeds the current best method by over 5% and 6% on the VCcloth and PRCC datasets respectively.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAL2097/_p
부
@ARTICLE{e105-a_8_1170,
author={Liwei WANG, Yanduo ZHANG, Tao LU, Wenhua FANG, Yu WANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multi Feature Fusion Attention Learning for Clothing-Changing Person Re-Identification},
year={2022},
volume={E105-A},
number={8},
pages={1170-1174},
abstract={Person re-identification (Re-ID) aims to match the same pedestrain identity images across different camera views. Because pedestrians will change clothes frequently for a relatively long time, while many current methods rely heavily on color appearance information or only focus on the person biometric features, these methods make the performance dropped apparently when it is applied to Clohting-Changing. To relieve this dilemma, we proposed a novel Multi Feature Fusion Attention Network (MFFAN), which learns the fine-grained local features. Then we introduced a Clothing Adaptive Attention (CAA) module, which can integrate multiple granularity features to guide model to learn pedestrain's biometric feature. Meanwhile, in order to fully verify the performance of our method on clothing-changing Re-ID problem, we designed a Clothing Generation Network (CGN), which can generate multiple pictures of the same identity wearing different clothes. Finally, experimental results show that our method exceeds the current best method by over 5% and 6% on the VCcloth and PRCC datasets respectively.},
keywords={},
doi={10.1587/transfun.2021EAL2097},
ISSN={1745-1337},
month={August},}
부
TY - JOUR
TI - Multi Feature Fusion Attention Learning for Clothing-Changing Person Re-Identification
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1170
EP - 1174
AU - Liwei WANG
AU - Yanduo ZHANG
AU - Tao LU
AU - Wenhua FANG
AU - Yu WANG
PY - 2022
DO - 10.1587/transfun.2021EAL2097
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2022
AB - Person re-identification (Re-ID) aims to match the same pedestrain identity images across different camera views. Because pedestrians will change clothes frequently for a relatively long time, while many current methods rely heavily on color appearance information or only focus on the person biometric features, these methods make the performance dropped apparently when it is applied to Clohting-Changing. To relieve this dilemma, we proposed a novel Multi Feature Fusion Attention Network (MFFAN), which learns the fine-grained local features. Then we introduced a Clothing Adaptive Attention (CAA) module, which can integrate multiple granularity features to guide model to learn pedestrain's biometric feature. Meanwhile, in order to fully verify the performance of our method on clothing-changing Re-ID problem, we designed a Clothing Generation Network (CGN), which can generate multiple pictures of the same identity wearing different clothes. Finally, experimental results show that our method exceeds the current best method by over 5% and 6% on the VCcloth and PRCC datasets respectively.
ER -