Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177144993> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3177144993 abstract "Conventional pedestrian attribute recognition methods typically rely on the assumption that enough well-labeled training samples are available. However, it is hard to be satisfied due to the unaffordable cost of human annotation, especially on big surveillance data. To address this problem, we propose a novel task-semi-supervised pedestrian attribute recognition (Semi-PAR), in which only a few limited labeled data and plenty of unlabeled data are available during training. We tackle the Semi-PAR problem by presenting a novel semi-supervised learning framework. In this framework, a PAR network is firstly designed to extract attribute-specific features, and adopts a similarity graph-based algorithm to generate pseudo-labels. Then we utilize the relationship of each attribute to modify the pseudo-labels, and feed them back to the PAR network to guide the training. Finally, a harmonic confidence loss is introduced to diminish the impact of harmful pseudo-labels. Experiments on three widely-used datasets verify the superiority of our method." @default.
- W3177144993 created "2021-07-05" @default.
- W3177144993 creator A5023918894 @default.
- W3177144993 creator A5032932242 @default.
- W3177144993 creator A5045281526 @default.
- W3177144993 creator A5047835985 @default.
- W3177144993 creator A5058066577 @default.
- W3177144993 creator A5070755370 @default.
- W3177144993 date "2021-07-05" @default.
- W3177144993 modified "2023-09-27" @default.
- W3177144993 title "Generate And Adjust: A Novel Framework For Semi-Supervised Pedestrian Attribute Recognition" @default.
- W3177144993 doi "https://doi.org/10.1109/icmew53276.2021.9455965" @default.
- W3177144993 hasPublicationYear "2021" @default.
- W3177144993 type Work @default.
- W3177144993 sameAs 3177144993 @default.
- W3177144993 citedByCount "0" @default.
- W3177144993 crossrefType "proceedings-article" @default.
- W3177144993 hasAuthorship W3177144993A5023918894 @default.
- W3177144993 hasAuthorship W3177144993A5032932242 @default.
- W3177144993 hasAuthorship W3177144993A5045281526 @default.
- W3177144993 hasAuthorship W3177144993A5047835985 @default.
- W3177144993 hasAuthorship W3177144993A5058066577 @default.
- W3177144993 hasAuthorship W3177144993A5070755370 @default.
- W3177144993 hasConcept C103278499 @default.
- W3177144993 hasConcept C115961682 @default.
- W3177144993 hasConcept C119857082 @default.
- W3177144993 hasConcept C124101348 @default.
- W3177144993 hasConcept C127413603 @default.
- W3177144993 hasConcept C132525143 @default.
- W3177144993 hasConcept C153180895 @default.
- W3177144993 hasConcept C154945302 @default.
- W3177144993 hasConcept C162324750 @default.
- W3177144993 hasConcept C187736073 @default.
- W3177144993 hasConcept C22212356 @default.
- W3177144993 hasConcept C2776145971 @default.
- W3177144993 hasConcept C2776321320 @default.
- W3177144993 hasConcept C2777113093 @default.
- W3177144993 hasConcept C2780451532 @default.
- W3177144993 hasConcept C41008148 @default.
- W3177144993 hasConcept C51632099 @default.
- W3177144993 hasConcept C80444323 @default.
- W3177144993 hasConceptScore W3177144993C103278499 @default.
- W3177144993 hasConceptScore W3177144993C115961682 @default.
- W3177144993 hasConceptScore W3177144993C119857082 @default.
- W3177144993 hasConceptScore W3177144993C124101348 @default.
- W3177144993 hasConceptScore W3177144993C127413603 @default.
- W3177144993 hasConceptScore W3177144993C132525143 @default.
- W3177144993 hasConceptScore W3177144993C153180895 @default.
- W3177144993 hasConceptScore W3177144993C154945302 @default.
- W3177144993 hasConceptScore W3177144993C162324750 @default.
- W3177144993 hasConceptScore W3177144993C187736073 @default.
- W3177144993 hasConceptScore W3177144993C22212356 @default.
- W3177144993 hasConceptScore W3177144993C2776145971 @default.
- W3177144993 hasConceptScore W3177144993C2776321320 @default.
- W3177144993 hasConceptScore W3177144993C2777113093 @default.
- W3177144993 hasConceptScore W3177144993C2780451532 @default.
- W3177144993 hasConceptScore W3177144993C41008148 @default.
- W3177144993 hasConceptScore W3177144993C51632099 @default.
- W3177144993 hasConceptScore W3177144993C80444323 @default.
- W3177144993 hasFunder F4320337504 @default.
- W3177144993 hasLocation W31771449931 @default.
- W3177144993 hasOpenAccess W3177144993 @default.
- W3177144993 hasPrimaryLocation W31771449931 @default.
- W3177144993 hasRelatedWork W151193258 @default.
- W3177144993 hasRelatedWork W1607472309 @default.
- W3177144993 hasRelatedWork W1942954136 @default.
- W3177144993 hasRelatedWork W2762452805 @default.
- W3177144993 hasRelatedWork W2900794075 @default.
- W3177144993 hasRelatedWork W2949070856 @default.
- W3177144993 hasRelatedWork W3183633970 @default.
- W3177144993 hasRelatedWork W4288093989 @default.
- W3177144993 hasRelatedWork W4302828163 @default.
- W3177144993 hasRelatedWork W67838485 @default.
- W3177144993 isParatext "false" @default.
- W3177144993 isRetracted "false" @default.
- W3177144993 magId "3177144993" @default.
- W3177144993 workType "article" @default.