Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386092797> ?p ?o ?g. }
- W4386092797 abstract "Abstract At present, occlusion and similar appearance pose serious challenges to the task of person re-identification. In this work, we propose an efficient multi-scale channel attention network (EMCA) to learn robust and more discriminative features to solve these problems. Specifically, we designed a novel cross-channel attention module (CCAM) in EMCA and placed it after different layers in the backbone. The CCAM includes local cross-channel interaction (LCI) and channel weight integration (CWI). LCI focuses on both the maximum pooling features and the average pooling features to generate channel weights through convolutional layers, respectively. CWI combines the two channel weights to generate richer and more discriminant channel weights. Experiments on four popular person Re-ID datasets (Market-1501, DukeMTMC-ReID, CUHK-03 (detected) and MSMT17) show that the performance of our EMCA is consistently significantly superior to the existing state-of-the-art methods." @default.
- W4386092797 created "2023-08-24" @default.
- W4386092797 creator A5022256556 @default.
- W4386092797 creator A5028258004 @default.
- W4386092797 creator A5030444996 @default.
- W4386092797 creator A5052729337 @default.
- W4386092797 creator A5056955855 @default.
- W4386092797 creator A5072350518 @default.
- W4386092797 date "2023-08-23" @default.
- W4386092797 modified "2023-09-27" @default.
- W4386092797 title "An efficient multi-scale channel attention network for person re-identification" @default.
- W4386092797 cites W1982925187 @default.
- W4386092797 cites W2108598243 @default.
- W4386092797 cites W2204750386 @default.
- W4386092797 cites W2511791013 @default.
- W4386092797 cites W2586899202 @default.
- W4386092797 cites W2752782242 @default.
- W4386092797 cites W2884585870 @default.
- W4386092797 cites W2962858109 @default.
- W4386092797 cites W2963047834 @default.
- W4386092797 cites W2967515867 @default.
- W4386092797 cites W2990827756 @default.
- W4386092797 cites W2998792609 @default.
- W4386092797 cites W3000388098 @default.
- W4386092797 cites W3006714671 @default.
- W4386092797 cites W3034552520 @default.
- W4386092797 cites W3034580371 @default.
- W4386092797 cites W3034611771 @default.
- W4386092797 cites W3035444456 @default.
- W4386092797 cites W3035738486 @default.
- W4386092797 cites W3039204154 @default.
- W4386092797 cites W3042857285 @default.
- W4386092797 cites W3097870364 @default.
- W4386092797 cites W3105159632 @default.
- W4386092797 cites W3106396328 @default.
- W4386092797 cites W3107308941 @default.
- W4386092797 cites W3120139554 @default.
- W4386092797 cites W3123416309 @default.
- W4386092797 cites W3124582122 @default.
- W4386092797 cites W3128498158 @default.
- W4386092797 cites W3128690020 @default.
- W4386092797 cites W3133793254 @default.
- W4386092797 cites W3134190557 @default.
- W4386092797 cites W3138516171 @default.
- W4386092797 cites W3173827247 @default.
- W4386092797 cites W3175823695 @default.
- W4386092797 cites W3180036565 @default.
- W4386092797 cites W3180614977 @default.
- W4386092797 cites W3195399086 @default.
- W4386092797 cites W3202312310 @default.
- W4386092797 cites W3202893281 @default.
- W4386092797 cites W3208382980 @default.
- W4386092797 cites W3217568419 @default.
- W4386092797 cites W4205720260 @default.
- W4386092797 cites W4214736485 @default.
- W4386092797 cites W4284973184 @default.
- W4386092797 cites W4312453698 @default.
- W4386092797 cites W4312633566 @default.
- W4386092797 cites W4312951616 @default.
- W4386092797 cites W4319299883 @default.
- W4386092797 cites W4376272248 @default.
- W4386092797 doi "https://doi.org/10.1007/s00371-023-03049-9" @default.
- W4386092797 hasPublicationYear "2023" @default.
- W4386092797 type Work @default.
- W4386092797 citedByCount "0" @default.
- W4386092797 crossrefType "journal-article" @default.
- W4386092797 hasAuthorship W4386092797A5022256556 @default.
- W4386092797 hasAuthorship W4386092797A5028258004 @default.
- W4386092797 hasAuthorship W4386092797A5030444996 @default.
- W4386092797 hasAuthorship W4386092797A5052729337 @default.
- W4386092797 hasAuthorship W4386092797A5056955855 @default.
- W4386092797 hasAuthorship W4386092797A5072350518 @default.
- W4386092797 hasBestOaLocation W43860927971 @default.
- W4386092797 hasConcept C116834253 @default.
- W4386092797 hasConcept C119857082 @default.
- W4386092797 hasConcept C121332964 @default.
- W4386092797 hasConcept C127162648 @default.
- W4386092797 hasConcept C153180895 @default.
- W4386092797 hasConcept C154945302 @default.
- W4386092797 hasConcept C162324750 @default.
- W4386092797 hasConcept C187736073 @default.
- W4386092797 hasConcept C2778755073 @default.
- W4386092797 hasConcept C2780451532 @default.
- W4386092797 hasConcept C41008148 @default.
- W4386092797 hasConcept C59822182 @default.
- W4386092797 hasConcept C62520636 @default.
- W4386092797 hasConcept C70437156 @default.
- W4386092797 hasConcept C76155785 @default.
- W4386092797 hasConcept C81363708 @default.
- W4386092797 hasConcept C86803240 @default.
- W4386092797 hasConcept C97931131 @default.
- W4386092797 hasConceptScore W4386092797C116834253 @default.
- W4386092797 hasConceptScore W4386092797C119857082 @default.
- W4386092797 hasConceptScore W4386092797C121332964 @default.
- W4386092797 hasConceptScore W4386092797C127162648 @default.
- W4386092797 hasConceptScore W4386092797C153180895 @default.
- W4386092797 hasConceptScore W4386092797C154945302 @default.
- W4386092797 hasConceptScore W4386092797C162324750 @default.
- W4386092797 hasConceptScore W4386092797C187736073 @default.
- W4386092797 hasConceptScore W4386092797C2778755073 @default.