Matches in SemOpenAlex for { <https://semopenalex.org/work/W3026128218> ?p ?o ?g. }
- W3026128218 abstract "Despite various methods are proposed to make progress in pedestrian attribute recognition, a crucial problem on existing datasets is often neglected, namely, a large number of identical pedestrian identities in train and test set, which is not consistent with practical application. Thus, images of the same pedestrian identity in train set and test set are extremely similar, leading to overestimated performance of state-of-the-art methods on existing datasets. To address this problem, we propose two realistic datasets PETAtextsubscript{$zs$} and RAPv2textsubscript{$zs$} following zero-shot setting of pedestrian identities based on PETA and RAPv2 datasets. Furthermore, compared to our strong baseline method, we have observed that recent state-of-the-art methods can not make performance improvement on PETA, RAPv2, PETAtextsubscript{$zs$} and RAPv2textsubscript{$zs$}. Thus, through solving the inherent attribute imbalance in pedestrian attribute recognition, an efficient method is proposed to further improve the performance. Experiments on existing and proposed datasets verify the superiority of our method by achieving state-of-the-art performance." @default.
- W3026128218 created "2020-05-29" @default.
- W3026128218 creator A5028693655 @default.
- W3026128218 creator A5043657487 @default.
- W3026128218 creator A5047010855 @default.
- W3026128218 creator A5049493630 @default.
- W3026128218 creator A5074896945 @default.
- W3026128218 date "2020-05-25" @default.
- W3026128218 modified "2023-09-27" @default.
- W3026128218 title "Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method." @default.
- W3026128218 cites W1999705173 @default.
- W3026128218 cites W2058102599 @default.
- W3026128218 cites W2064675550 @default.
- W3026128218 cites W2111025459 @default.
- W3026128218 cites W2155541015 @default.
- W3026128218 cites W2194775991 @default.
- W3026128218 cites W2295107390 @default.
- W3026128218 cites W2308869522 @default.
- W3026128218 cites W2410968923 @default.
- W3026128218 cites W2440599146 @default.
- W3026128218 cites W2554816096 @default.
- W3026128218 cites W2565639579 @default.
- W3026128218 cites W2604463754 @default.
- W3026128218 cites W2767106145 @default.
- W3026128218 cites W2867270703 @default.
- W3026128218 cites W2895281799 @default.
- W3026128218 cites W2896249043 @default.
- W3026128218 cites W2898491875 @default.
- W3026128218 cites W2921393178 @default.
- W3026128218 cites W2954765307 @default.
- W3026128218 cites W2957702778 @default.
- W3026128218 cites W2962858109 @default.
- W3026128218 cites W2963351448 @default.
- W3026128218 cites W2963365374 @default.
- W3026128218 cites W2963420686 @default.
- W3026128218 cites W2963466847 @default.
- W3026128218 cites W2963620099 @default.
- W3026128218 cites W2963691377 @default.
- W3026128218 cites W2964248351 @default.
- W3026128218 cites W2969985801 @default.
- W3026128218 cites W2970941190 @default.
- W3026128218 cites W2986999591 @default.
- W3026128218 cites W2992996860 @default.
- W3026128218 cites W3101227480 @default.
- W3026128218 cites W603908379 @default.
- W3026128218 cites W7746136 @default.
- W3026128218 hasPublicationYear "2020" @default.
- W3026128218 type Work @default.
- W3026128218 sameAs 3026128218 @default.
- W3026128218 citedByCount "3" @default.
- W3026128218 countsByYear W30261282182020 @default.
- W3026128218 countsByYear W30261282182021 @default.
- W3026128218 crossrefType "posted-content" @default.
- W3026128218 hasAuthorship W3026128218A5028693655 @default.
- W3026128218 hasAuthorship W3026128218A5043657487 @default.
- W3026128218 hasAuthorship W3026128218A5047010855 @default.
- W3026128218 hasAuthorship W3026128218A5049493630 @default.
- W3026128218 hasAuthorship W3026128218A5074896945 @default.
- W3026128218 hasConcept C111368507 @default.
- W3026128218 hasConcept C11413529 @default.
- W3026128218 hasConcept C115961682 @default.
- W3026128218 hasConcept C119857082 @default.
- W3026128218 hasConcept C121332964 @default.
- W3026128218 hasConcept C124101348 @default.
- W3026128218 hasConcept C12725497 @default.
- W3026128218 hasConcept C127313418 @default.
- W3026128218 hasConcept C127413603 @default.
- W3026128218 hasConcept C153180895 @default.
- W3026128218 hasConcept C154945302 @default.
- W3026128218 hasConcept C169903167 @default.
- W3026128218 hasConcept C177264268 @default.
- W3026128218 hasConcept C178790620 @default.
- W3026128218 hasConcept C185592680 @default.
- W3026128218 hasConcept C199360897 @default.
- W3026128218 hasConcept C22212356 @default.
- W3026128218 hasConcept C24890656 @default.
- W3026128218 hasConcept C2777113093 @default.
- W3026128218 hasConcept C2778344882 @default.
- W3026128218 hasConcept C2778355321 @default.
- W3026128218 hasConcept C41008148 @default.
- W3026128218 hasConcept C48103436 @default.
- W3026128218 hasConceptScore W3026128218C111368507 @default.
- W3026128218 hasConceptScore W3026128218C11413529 @default.
- W3026128218 hasConceptScore W3026128218C115961682 @default.
- W3026128218 hasConceptScore W3026128218C119857082 @default.
- W3026128218 hasConceptScore W3026128218C121332964 @default.
- W3026128218 hasConceptScore W3026128218C124101348 @default.
- W3026128218 hasConceptScore W3026128218C12725497 @default.
- W3026128218 hasConceptScore W3026128218C127313418 @default.
- W3026128218 hasConceptScore W3026128218C127413603 @default.
- W3026128218 hasConceptScore W3026128218C153180895 @default.
- W3026128218 hasConceptScore W3026128218C154945302 @default.
- W3026128218 hasConceptScore W3026128218C169903167 @default.
- W3026128218 hasConceptScore W3026128218C177264268 @default.
- W3026128218 hasConceptScore W3026128218C178790620 @default.
- W3026128218 hasConceptScore W3026128218C185592680 @default.
- W3026128218 hasConceptScore W3026128218C199360897 @default.
- W3026128218 hasConceptScore W3026128218C22212356 @default.
- W3026128218 hasConceptScore W3026128218C24890656 @default.
- W3026128218 hasConceptScore W3026128218C2777113093 @default.