Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200445214> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3200445214 abstract "While recent studies on pedestrian attribute recognition have shown remarkable progress in leveraging complicated networks and attention mechanisms, most of them neglect the inter-image relations and an important prior: spatial consistency and semantic consistency of attributes under surveillance scenarios. The spatial locations of the same attribute should be consistent between different pedestrian images, e.g., the hat attribute and the boots attribute are always located at the top and bottom of the picture respectively. In addition, the inherent semantic feature of the hat attribute should be consistent, whether it is a baseball cap, beret, or helmet. To fully exploit inter-image relations and aggregate human prior in the model learning process, we construct a Spatial and Semantic Consistency (SSC) framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Specifically, we first propose a spatial consistency regularization to focus on reliable and stable attribute-related regions. Based on the precise attribute locations, we further propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. We conduct extensive experiments on popular benchmarks including PA100K, RAP, and PETA. Results show that the proposed method performs favorably against state- of-the-art methods without increasing parameters." @default.
- W3200445214 created "2021-09-27" @default.
- W3200445214 creator A5028693655 @default.
- W3200445214 creator A5043657487 @default.
- W3200445214 creator A5047010855 @default.
- W3200445214 date "2021-10-01" @default.
- W3200445214 modified "2023-10-02" @default.
- W3200445214 title "Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition" @default.
- W3200445214 cites W1962468782 @default.
- W3200445214 cites W1999705173 @default.
- W3200445214 cites W2064675550 @default.
- W3200445214 cites W2111025459 @default.
- W3200445214 cites W2194775991 @default.
- W3200445214 cites W2295107390 @default.
- W3200445214 cites W2410968923 @default.
- W3200445214 cites W2565639579 @default.
- W3200445214 cites W2896249043 @default.
- W3200445214 cites W2898491875 @default.
- W3200445214 cites W2954765307 @default.
- W3200445214 cites W2957702778 @default.
- W3200445214 cites W2963365374 @default.
- W3200445214 cites W2964248351 @default.
- W3200445214 cites W2986999591 @default.
- W3200445214 cites W3035590987 @default.
- W3200445214 cites W3037140251 @default.
- W3200445214 doi "https://doi.org/10.1109/iccv48922.2021.00100" @default.
- W3200445214 hasPublicationYear "2021" @default.
- W3200445214 type Work @default.
- W3200445214 sameAs 3200445214 @default.
- W3200445214 citedByCount "14" @default.
- W3200445214 countsByYear W32004452142022 @default.
- W3200445214 countsByYear W32004452142023 @default.
- W3200445214 crossrefType "proceedings-article" @default.
- W3200445214 hasAuthorship W3200445214A5028693655 @default.
- W3200445214 hasAuthorship W3200445214A5043657487 @default.
- W3200445214 hasAuthorship W3200445214A5047010855 @default.
- W3200445214 hasBestOaLocation W32004452142 @default.
- W3200445214 hasConcept C124101348 @default.
- W3200445214 hasConcept C138885662 @default.
- W3200445214 hasConcept C153180895 @default.
- W3200445214 hasConcept C154945302 @default.
- W3200445214 hasConcept C165696696 @default.
- W3200445214 hasConcept C166957645 @default.
- W3200445214 hasConcept C205649164 @default.
- W3200445214 hasConcept C27511587 @default.
- W3200445214 hasConcept C2776135515 @default.
- W3200445214 hasConcept C2776401178 @default.
- W3200445214 hasConcept C2776436953 @default.
- W3200445214 hasConcept C2777113093 @default.
- W3200445214 hasConcept C38652104 @default.
- W3200445214 hasConcept C41008148 @default.
- W3200445214 hasConcept C41895202 @default.
- W3200445214 hasConcept C97931131 @default.
- W3200445214 hasConceptScore W3200445214C124101348 @default.
- W3200445214 hasConceptScore W3200445214C138885662 @default.
- W3200445214 hasConceptScore W3200445214C153180895 @default.
- W3200445214 hasConceptScore W3200445214C154945302 @default.
- W3200445214 hasConceptScore W3200445214C165696696 @default.
- W3200445214 hasConceptScore W3200445214C166957645 @default.
- W3200445214 hasConceptScore W3200445214C205649164 @default.
- W3200445214 hasConceptScore W3200445214C27511587 @default.
- W3200445214 hasConceptScore W3200445214C2776135515 @default.
- W3200445214 hasConceptScore W3200445214C2776401178 @default.
- W3200445214 hasConceptScore W3200445214C2776436953 @default.
- W3200445214 hasConceptScore W3200445214C2777113093 @default.
- W3200445214 hasConceptScore W3200445214C38652104 @default.
- W3200445214 hasConceptScore W3200445214C41008148 @default.
- W3200445214 hasConceptScore W3200445214C41895202 @default.
- W3200445214 hasConceptScore W3200445214C97931131 @default.
- W3200445214 hasFunder F4320321001 @default.
- W3200445214 hasFunder F4320321133 @default.
- W3200445214 hasLocation W32004452141 @default.
- W3200445214 hasLocation W32004452142 @default.
- W3200445214 hasOpenAccess W3200445214 @default.
- W3200445214 hasPrimaryLocation W32004452141 @default.
- W3200445214 hasRelatedWork W1652783584 @default.
- W3200445214 hasRelatedWork W1971623867 @default.
- W3200445214 hasRelatedWork W1982770690 @default.
- W3200445214 hasRelatedWork W1990254706 @default.
- W3200445214 hasRelatedWork W2024160000 @default.
- W3200445214 hasRelatedWork W2404514746 @default.
- W3200445214 hasRelatedWork W2546942002 @default.
- W3200445214 hasRelatedWork W2729514902 @default.
- W3200445214 hasRelatedWork W2773500201 @default.
- W3200445214 hasRelatedWork W2971458799 @default.
- W3200445214 isParatext "false" @default.
- W3200445214 isRetracted "false" @default.
- W3200445214 magId "3200445214" @default.
- W3200445214 workType "article" @default.