Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels
| Autor: | Shuai Wan, Ke Chen, Shun Zhang, Jiang Wei, Yantao He, Shaohui Mei |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
General Computer Science
Computer science Feature extraction Multi-task learning multi-task learning convolutional neural network 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Person re-identification Discriminative model Robustness (computer science) 0202 electrical engineering electronic engineering information engineering General Materials Science 0105 earth and related environmental sciences Artificial neural network business.industry General Engineering Feature (computer vision) Metric (mathematics) 020201 artificial intelligence & image processing Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business computer lcsh:TK1-9971 attribute learning |
| Zdroj: | IEEE Access, Vol 7, Pp 126116-126126 (2019) Zhang, S, He, Y, Wei, J, Mei, S, Wan, S & Chen, K 2019, ' Person Re-identification with Joint Verification and Identification of Identity-Attribute Labels ', IEEE Access . https://doi.org/10.1109/ACCESS.2019.2939071 |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/ACCESS.2019.2939071 |
| Popis: | One of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, etc. This makes person ReID among multiple cameras still challenging. This work is motivated to learn mid-level human attributes which are robust to visual appearance variations and could be used as efficient features for person matching. We propose a supervised multi-task learning framework which considers attribute label information with joint identification-verification network to simultaneously learn an attribute-semantic and identity-discriminative feature representation. Specifically, this framework adopts the part-based deep neural network and learn three different tasks simultaneously: person identification, person verifications and attribute identification, so as to discover and capture concurrently complementary discriminative information about a person image from global and local image features and mid-level attribute features in one deep neural network. With the multi-task learning architecture, we obtain a discriminative model that reaches a synergy in distinguishing different person images, as manifested with the competitive accuracy on three person ReID datasets: Market1501, DukeMTMC-reID and VIPeR. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|