Matches in SemOpenAlex for { <https://semopenalex.org/work/W3164861657> ?p ?o ?g. }
- W3164861657 abstract "Person Re-ID is challenged by background clutter, body misalignment and part missing. In this paper, we propose a reliable part-based multiple levels attention deep network to learn multiple scales salience representation. In particular, person alignment and key point detection are sequentially carried out to locate three relative stable body components, then fused attention (FA) mode is designed to capture the fine-grained salient features from effective spatial of valuable channels of each part, regional attention mode is succeeded to weight the importance of different parts for highlighting the representative parts while suppressing the valueless ones. A late fusion-based multiple-task loss is finally adopted to further optimize the valuable feature representation. Experimental results demonstrate that the proposed method achieves state-of-the-art performances on three challenging benchmarks: Market-1501, DukeMTMC-reID and CUHK03." @default.
- W3164861657 created "2021-06-07" @default.
- W3164861657 creator A5028619141 @default.
- W3164861657 creator A5046361934 @default.
- W3164861657 creator A5052945329 @default.
- W3164861657 creator A5076207109 @default.
- W3164861657 creator A5082088474 @default.
- W3164861657 date "2021-05-25" @default.
- W3164861657 modified "2023-09-28" @default.
- W3164861657 title "Reliable Part Guided Multiple Level Attention Learning for Person Re-Identification" @default.
- W3164861657 cites W1928419358 @default.
- W3164861657 cites W2109255472 @default.
- W3164861657 cites W2204750386 @default.
- W3164861657 cites W2289130514 @default.
- W3164861657 cites W2300840837 @default.
- W3164861657 cites W2344837812 @default.
- W3164861657 cites W2382036597 @default.
- W3164861657 cites W2467139031 @default.
- W3164861657 cites W2471048925 @default.
- W3164861657 cites W2491664569 @default.
- W3164861657 cites W2585635281 @default.
- W3164861657 cites W2604211872 @default.
- W3164861657 cites W2604463754 @default.
- W3164861657 cites W2724213014 @default.
- W3164861657 cites W2736410039 @default.
- W3164861657 cites W2738406610 @default.
- W3164861657 cites W2752782242 @default.
- W3164861657 cites W2798775284 @default.
- W3164861657 cites W2884585870 @default.
- W3164861657 cites W2886753155 @default.
- W3164861657 cites W2891175865 @default.
- W3164861657 cites W2902773991 @default.
- W3164861657 cites W2903410716 @default.
- W3164861657 cites W2909318183 @default.
- W3164861657 cites W2910414172 @default.
- W3164861657 cites W2942900304 @default.
- W3164861657 cites W2958327660 @default.
- W3164861657 cites W2962926870 @default.
- W3164861657 cites W2963180826 @default.
- W3164861657 cites W2963365374 @default.
- W3164861657 cites W2963383990 @default.
- W3164861657 cites W2963438548 @default.
- W3164861657 cites W2963637710 @default.
- W3164861657 cites W2963727650 @default.
- W3164861657 cites W2963805953 @default.
- W3164861657 cites W2963842104 @default.
- W3164861657 cites W2963910742 @default.
- W3164861657 cites W2964044605 @default.
- W3164861657 cites W2964130064 @default.
- W3164861657 cites W2964163358 @default.
- W3164861657 cites W2964260687 @default.
- W3164861657 cites W2964304299 @default.
- W3164861657 cites W2967359135 @default.
- W3164861657 cites W2968554659 @default.
- W3164861657 cites W2968770874 @default.
- W3164861657 cites W2971765950 @default.
- W3164861657 cites W2979931389 @default.
- W3164861657 cites W2988964414 @default.
- W3164861657 cites W2989789217 @default.
- W3164861657 cites W2990827756 @default.
- W3164861657 cites W3008177173 @default.
- W3164861657 cites W3008207445 @default.
- W3164861657 cites W3010835976 @default.
- W3164861657 cites W3010938738 @default.
- W3164861657 cites W3033060862 @default.
- W3164861657 cites W3089821037 @default.
- W3164861657 cites W3100555577 @default.
- W3164861657 doi "https://doi.org/10.1142/s0218126621502467" @default.
- W3164861657 hasPublicationYear "2021" @default.
- W3164861657 type Work @default.
- W3164861657 sameAs 3164861657 @default.
- W3164861657 citedByCount "1" @default.
- W3164861657 countsByYear W31648616572022 @default.
- W3164861657 crossrefType "journal-article" @default.
- W3164861657 hasAuthorship W3164861657A5028619141 @default.
- W3164861657 hasAuthorship W3164861657A5046361934 @default.
- W3164861657 hasAuthorship W3164861657A5052945329 @default.
- W3164861657 hasAuthorship W3164861657A5076207109 @default.
- W3164861657 hasAuthorship W3164861657A5082088474 @default.
- W3164861657 hasConcept C108154423 @default.
- W3164861657 hasConcept C119857082 @default.
- W3164861657 hasConcept C127413603 @default.
- W3164861657 hasConcept C132094186 @default.
- W3164861657 hasConcept C138885662 @default.
- W3164861657 hasConcept C153180895 @default.
- W3164861657 hasConcept C154945302 @default.
- W3164861657 hasConcept C17744445 @default.
- W3164861657 hasConcept C199539241 @default.
- W3164861657 hasConcept C201995342 @default.
- W3164861657 hasConcept C2776359362 @default.
- W3164861657 hasConcept C2776401178 @default.
- W3164861657 hasConcept C2780451532 @default.
- W3164861657 hasConcept C2780719617 @default.
- W3164861657 hasConcept C2993807640 @default.
- W3164861657 hasConcept C41008148 @default.
- W3164861657 hasConcept C41895202 @default.
- W3164861657 hasConcept C554190296 @default.
- W3164861657 hasConcept C59404180 @default.
- W3164861657 hasConcept C76155785 @default.
- W3164861657 hasConcept C94625758 @default.