Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379780462> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4379780462 abstract "Pedestrian attribute recognition has attracted extensive attention in surveillance scenarios. Many researchers treat it as a multi-label classification problem. However, they ignore the relations among attributes. For example, long hair and female often appear together at the semantic level, and there exists an overlap between their attribute-related regions at the visual level, e.g., female-related regions including long-hair-related head area and skirt-related areas. There is a correspondence between the semantic level and the visual level. However, existing relation-based methods which explore relations among attributes mostly ignore the correspondence between semantic and visual levels in relations among attributes. Our main contribution lies in proposing a novel end-to-end trainable Attribute-related Graph Visual Dependencies (AGVD) framework that can learn the dependencies of attributes based on extracted attribute-related visual features. Moreover, we propose a Graph Fusion mechanism to guide the attribute-related graph generation and pruning via semantic relations innovatively. We conduct experiments on three large-scale pedestrian attribute datasets. The experiments on PETA, RAP, and PA-100k have demonstrated that the AGVD outperforms the previous state-of-the-art methods." @default.
- W4379780462 created "2023-06-09" @default.
- W4379780462 creator A5011765589 @default.
- W4379780462 creator A5024501453 @default.
- W4379780462 creator A5031234889 @default.
- W4379780462 creator A5045163085 @default.
- W4379780462 date "2023-06-08" @default.
- W4379780462 modified "2023-10-18" @default.
- W4379780462 title "Attribute-related graph visual dependencies for pedestrian attribute recognition" @default.
- W4379780462 doi "https://doi.org/10.1117/12.2681033" @default.
- W4379780462 hasPublicationYear "2023" @default.
- W4379780462 type Work @default.
- W4379780462 citedByCount "0" @default.
- W4379780462 crossrefType "proceedings-article" @default.
- W4379780462 hasAuthorship W4379780462A5011765589 @default.
- W4379780462 hasAuthorship W4379780462A5024501453 @default.
- W4379780462 hasAuthorship W4379780462A5031234889 @default.
- W4379780462 hasAuthorship W4379780462A5045163085 @default.
- W4379780462 hasConcept C108010975 @default.
- W4379780462 hasConcept C119857082 @default.
- W4379780462 hasConcept C124101348 @default.
- W4379780462 hasConcept C127413603 @default.
- W4379780462 hasConcept C132525143 @default.
- W4379780462 hasConcept C153180895 @default.
- W4379780462 hasConcept C154945302 @default.
- W4379780462 hasConcept C204321447 @default.
- W4379780462 hasConcept C22212356 @default.
- W4379780462 hasConcept C23123220 @default.
- W4379780462 hasConcept C25343380 @default.
- W4379780462 hasConcept C2777113093 @default.
- W4379780462 hasConcept C41008148 @default.
- W4379780462 hasConcept C6557445 @default.
- W4379780462 hasConcept C80444323 @default.
- W4379780462 hasConcept C86803240 @default.
- W4379780462 hasConceptScore W4379780462C108010975 @default.
- W4379780462 hasConceptScore W4379780462C119857082 @default.
- W4379780462 hasConceptScore W4379780462C124101348 @default.
- W4379780462 hasConceptScore W4379780462C127413603 @default.
- W4379780462 hasConceptScore W4379780462C132525143 @default.
- W4379780462 hasConceptScore W4379780462C153180895 @default.
- W4379780462 hasConceptScore W4379780462C154945302 @default.
- W4379780462 hasConceptScore W4379780462C204321447 @default.
- W4379780462 hasConceptScore W4379780462C22212356 @default.
- W4379780462 hasConceptScore W4379780462C23123220 @default.
- W4379780462 hasConceptScore W4379780462C25343380 @default.
- W4379780462 hasConceptScore W4379780462C2777113093 @default.
- W4379780462 hasConceptScore W4379780462C41008148 @default.
- W4379780462 hasConceptScore W4379780462C6557445 @default.
- W4379780462 hasConceptScore W4379780462C80444323 @default.
- W4379780462 hasConceptScore W4379780462C86803240 @default.
- W4379780462 hasLocation W43797804621 @default.
- W4379780462 hasOpenAccess W4379780462 @default.
- W4379780462 hasPrimaryLocation W43797804621 @default.
- W4379780462 hasRelatedWork W2030478693 @default.
- W4379780462 hasRelatedWork W2357241418 @default.
- W4379780462 hasRelatedWork W2366644548 @default.
- W4379780462 hasRelatedWork W2376314740 @default.
- W4379780462 hasRelatedWork W2384888906 @default.
- W4379780462 hasRelatedWork W2961085424 @default.
- W4379780462 hasRelatedWork W3199608561 @default.
- W4379780462 hasRelatedWork W4286629047 @default.
- W4379780462 hasRelatedWork W4306674287 @default.
- W4379780462 hasRelatedWork W4224009465 @default.
- W4379780462 isParatext "false" @default.
- W4379780462 isRetracted "false" @default.
- W4379780462 workType "article" @default.