Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972595702> ?p ?o ?g. }
- W2972595702 endingPage "132447" @default.
- W2972595702 startingPage "132438" @default.
- W2972595702 abstract "Person re-identification has become increasing popular because of its widely application in computer vision. In this paper, we propose a novel, simple and efficient person re-id network called MPLFN. The network combines two tasks: the classification task and the metric learning task. In the classification task, we uniformly partition N feature parts from an image, and compute the person classification loss in each part separately. Computing the part loss separately guides the network to focus on every body part and learn discriminative representations for each of them. And then in the metric learning task, we recalculate the distance of two images by the shortest path between two sets of feature parts. Then the distances are put into a triplet loss to perform a dynamic part alignment during the training. With the joint learning of these two tasks, the performance of the network is significantly enhanced. Compared with existing person re-id works, MPLFN achieves a better performance on three mainstream person re-identification datasets. Extensive experiments have been conducted to validate our proposed method." @default.
- W2972595702 created "2019-09-19" @default.
- W2972595702 creator A5005228383 @default.
- W2972595702 creator A5016603628 @default.
- W2972595702 creator A5016625901 @default.
- W2972595702 creator A5020177243 @default.
- W2972595702 creator A5081308434 @default.
- W2972595702 date "2019-01-01" @default.
- W2972595702 modified "2023-10-16" @default.
- W2972595702 title "Person Re-Identification Based on Multi-Parts of Local Feature Network" @default.
- W2972595702 cites W1982925187 @default.
- W2972595702 cites W2108598243 @default.
- W2972595702 cites W2194775991 @default.
- W2972595702 cites W2204750386 @default.
- W2972595702 cites W2342611082 @default.
- W2972595702 cites W2467139031 @default.
- W2972595702 cites W2491664569 @default.
- W2972595702 cites W2511791013 @default.
- W2972595702 cites W2520774990 @default.
- W2972595702 cites W2584637367 @default.
- W2972595702 cites W2585635281 @default.
- W2972595702 cites W2724213014 @default.
- W2972595702 cites W2736410039 @default.
- W2972595702 cites W2761121566 @default.
- W2972595702 cites W2768610172 @default.
- W2972595702 cites W2798429327 @default.
- W2972595702 cites W2798550112 @default.
- W2972595702 cites W2798874329 @default.
- W2972595702 cites W2799185441 @default.
- W2972595702 cites W2891175865 @default.
- W2972595702 cites W2896888563 @default.
- W2972595702 cites W2904427185 @default.
- W2972595702 cites W2909398625 @default.
- W2972595702 cites W2912149104 @default.
- W2972595702 cites W2962706983 @default.
- W2972595702 cites W2962926870 @default.
- W2972595702 cites W2963383990 @default.
- W2972595702 cites W2963438548 @default.
- W2972595702 cites W2963805953 @default.
- W2972595702 cites W2963842104 @default.
- W2972595702 cites W2963975998 @default.
- W2972595702 cites W2964130064 @default.
- W2972595702 cites W2964173540 @default.
- W2972595702 doi "https://doi.org/10.1109/access.2019.2941002" @default.
- W2972595702 hasPublicationYear "2019" @default.
- W2972595702 type Work @default.
- W2972595702 sameAs 2972595702 @default.
- W2972595702 citedByCount "3" @default.
- W2972595702 countsByYear W29725957022020 @default.
- W2972595702 countsByYear W29725957022021 @default.
- W2972595702 countsByYear W29725957022022 @default.
- W2972595702 crossrefType "journal-article" @default.
- W2972595702 hasAuthorship W2972595702A5005228383 @default.
- W2972595702 hasAuthorship W2972595702A5016603628 @default.
- W2972595702 hasAuthorship W2972595702A5016625901 @default.
- W2972595702 hasAuthorship W2972595702A5020177243 @default.
- W2972595702 hasAuthorship W2972595702A5081308434 @default.
- W2972595702 hasBestOaLocation W29725957021 @default.
- W2972595702 hasConcept C114614502 @default.
- W2972595702 hasConcept C116834253 @default.
- W2972595702 hasConcept C119857082 @default.
- W2972595702 hasConcept C120665830 @default.
- W2972595702 hasConcept C121332964 @default.
- W2972595702 hasConcept C138885662 @default.
- W2972595702 hasConcept C153180895 @default.
- W2972595702 hasConcept C154945302 @default.
- W2972595702 hasConcept C162324750 @default.
- W2972595702 hasConcept C176217482 @default.
- W2972595702 hasConcept C187736073 @default.
- W2972595702 hasConcept C192209626 @default.
- W2972595702 hasConcept C21547014 @default.
- W2972595702 hasConcept C2776401178 @default.
- W2972595702 hasConcept C2780186347 @default.
- W2972595702 hasConcept C2780451532 @default.
- W2972595702 hasConcept C33923547 @default.
- W2972595702 hasConcept C38652104 @default.
- W2972595702 hasConcept C41008148 @default.
- W2972595702 hasConcept C41895202 @default.
- W2972595702 hasConcept C42812 @default.
- W2972595702 hasConcept C52622490 @default.
- W2972595702 hasConcept C59822182 @default.
- W2972595702 hasConcept C86803240 @default.
- W2972595702 hasConcept C97931131 @default.
- W2972595702 hasConceptScore W2972595702C114614502 @default.
- W2972595702 hasConceptScore W2972595702C116834253 @default.
- W2972595702 hasConceptScore W2972595702C119857082 @default.
- W2972595702 hasConceptScore W2972595702C120665830 @default.
- W2972595702 hasConceptScore W2972595702C121332964 @default.
- W2972595702 hasConceptScore W2972595702C138885662 @default.
- W2972595702 hasConceptScore W2972595702C153180895 @default.
- W2972595702 hasConceptScore W2972595702C154945302 @default.
- W2972595702 hasConceptScore W2972595702C162324750 @default.
- W2972595702 hasConceptScore W2972595702C176217482 @default.
- W2972595702 hasConceptScore W2972595702C187736073 @default.
- W2972595702 hasConceptScore W2972595702C192209626 @default.
- W2972595702 hasConceptScore W2972595702C21547014 @default.
- W2972595702 hasConceptScore W2972595702C2776401178 @default.
- W2972595702 hasConceptScore W2972595702C2780186347 @default.