Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215919575> ?p ?o ?g. }
- W3215919575 endingPage "156" @default.
- W3215919575 startingPage "136" @default.
- W3215919575 abstract "Person images captured by public surveillance cameras often have low resolutions (LRs), along with uncontrolled pose variations, background clutter and occlusion. These issues cause the resolution mismatch problem when matched with high-resolution (HR) gallery images (typically available during collection), harming the person re-identification (re-id) performance. While a number of methods have been introduced based on the joint learning of super-resolution and person re-id, they ignore specific discriminant identity information encoded in LR person images, leading to ineffective model performance. In this work, we propose a novel joint bilateral-resolution identity modeling method that concurrently performs HR-specific identity feature learning with super-resolution, LR-specific identity feature learning, and person re-id optimization. We also introduce an adaptive ensemble algorithm for handling different low resolutions. Extensive evaluations validate the advantages of our method over related state-of-the-art re-id and super-resolution methods on cross-resolution re-id benchmarks. An important discovery is that leveraging LR-specific identity information enables a simple cascade of super-resolution and person re-id learning to achieve state-of-the-art performance, without elaborate model design nor bells and whistles, which has not been investigated before." @default.
- W3215919575 created "2021-12-06" @default.
- W3215919575 creator A5025105802 @default.
- W3215919575 creator A5028643592 @default.
- W3215919575 creator A5034685928 @default.
- W3215919575 creator A5039302902 @default.
- W3215919575 creator A5049519486 @default.
- W3215919575 creator A5073801860 @default.
- W3215919575 creator A5079675572 @default.
- W3215919575 creator A5082605318 @default.
- W3215919575 date "2021-11-22" @default.
- W3215919575 modified "2023-10-17" @default.
- W3215919575 title "Joint Bilateral-Resolution Identity Modeling for Cross-Resolution Person Re-Identification" @default.
- W3215919575 cites W1518138188 @default.
- W3215919575 cites W1885185971 @default.
- W3215919575 cites W1919542679 @default.
- W3215919575 cites W1928419358 @default.
- W3215919575 cites W1949591461 @default.
- W3215919575 cites W1982925187 @default.
- W3215919575 cites W2066380143 @default.
- W3215919575 cites W2071399526 @default.
- W3215919575 cites W2089074647 @default.
- W3215919575 cites W2104978738 @default.
- W3215919575 cites W2114380981 @default.
- W3215919575 cites W2126791727 @default.
- W3215919575 cites W2162915993 @default.
- W3215919575 cites W2194775991 @default.
- W3215919575 cites W2204750386 @default.
- W3215919575 cites W2213726222 @default.
- W3215919575 cites W2214802144 @default.
- W3215919575 cites W2242218935 @default.
- W3215919575 cites W2258844511 @default.
- W3215919575 cites W2300840837 @default.
- W3215919575 cites W2342611082 @default.
- W3215919575 cites W2433217581 @default.
- W3215919575 cites W2503339013 @default.
- W3215919575 cites W2511791013 @default.
- W3215919575 cites W2586899202 @default.
- W3215919575 cites W2607041014 @default.
- W3215919575 cites W2747898905 @default.
- W3215919575 cites W2788162446 @default.
- W3215919575 cites W2807957650 @default.
- W3215919575 cites W2810967842 @default.
- W3215919575 cites W2866634454 @default.
- W3215919575 cites W2883348239 @default.
- W3215919575 cites W2905248226 @default.
- W3215919575 cites W2963049565 @default.
- W3215919575 cites W2963372104 @default.
- W3215919575 cites W2963470893 @default.
- W3215919575 cites W2963610452 @default.
- W3215919575 cites W2963690547 @default.
- W3215919575 cites W2963729050 @default.
- W3215919575 cites W2963805953 @default.
- W3215919575 cites W2963842104 @default.
- W3215919575 cites W2964289004 @default.
- W3215919575 cites W2964443374 @default.
- W3215919575 cites W2967515867 @default.
- W3215919575 cites W2979931389 @default.
- W3215919575 cites W2984040540 @default.
- W3215919575 cites W2984145721 @default.
- W3215919575 cites W2988964414 @default.
- W3215919575 cites W2990827756 @default.
- W3215919575 cites W2993954232 @default.
- W3215919575 cites W2998792609 @default.
- W3215919575 cites W3034457627 @default.
- W3215919575 cites W3034527052 @default.
- W3215919575 cites W3098711604 @default.
- W3215919575 cites W4317524344 @default.
- W3215919575 cites W54257720 @default.
- W3215919575 cites W760855798 @default.
- W3215919575 doi "https://doi.org/10.1007/s11263-021-01518-z" @default.
- W3215919575 hasPublicationYear "2021" @default.
- W3215919575 type Work @default.
- W3215919575 sameAs 3215919575 @default.
- W3215919575 citedByCount "5" @default.
- W3215919575 countsByYear W32159195752022 @default.
- W3215919575 countsByYear W32159195752023 @default.
- W3215919575 crossrefType "journal-article" @default.
- W3215919575 hasAuthorship W3215919575A5025105802 @default.
- W3215919575 hasAuthorship W3215919575A5028643592 @default.
- W3215919575 hasAuthorship W3215919575A5034685928 @default.
- W3215919575 hasAuthorship W3215919575A5039302902 @default.
- W3215919575 hasAuthorship W3215919575A5049519486 @default.
- W3215919575 hasAuthorship W3215919575A5073801860 @default.
- W3215919575 hasAuthorship W3215919575A5079675572 @default.
- W3215919575 hasAuthorship W3215919575A5082605318 @default.
- W3215919575 hasBestOaLocation W32159195752 @default.
- W3215919575 hasConcept C116834253 @default.
- W3215919575 hasConcept C119857082 @default.
- W3215919575 hasConcept C121332964 @default.
- W3215919575 hasConcept C127413603 @default.
- W3215919575 hasConcept C132094186 @default.
- W3215919575 hasConcept C138268822 @default.
- W3215919575 hasConcept C138885662 @default.
- W3215919575 hasConcept C153180895 @default.
- W3215919575 hasConcept C154945302 @default.
- W3215919575 hasConcept C170154142 @default.
- W3215919575 hasConcept C18555067 @default.