Matches in SemOpenAlex for { <https://semopenalex.org/work/W2247349754> ?p ?o ?g. }
- W2247349754 endingPage "892" @default.
- W2247349754 startingPage "878" @default.
- W2247349754 abstract "Fine-grained visual categorization is an emerging research area and has been attracting growing attention recently. Due to the large inter-class similarity and intra-class variance, it is extremely challenging to recognize objects in fine-grained domains. A traditional spatial pyramid matching model could obtain desirable results for the basic-level category classification by weak alignment, but may easily fail in fine-grained domains, since the discriminative features are extremely localized. This paper proposes a new framework for fine-grained visual categorization. First, an efficient part localization method incorporates semantic prior into geometric alignment. It detects the less deformable parts, such as the head of birds with a template-based model, and localizes other highly deformable parts with simple geometric alignment. Second, we learn one-vs-all features, which are simple and transplantable. The learned mid-level features are dimension friendly and more robust to outlier instances. Furthermore, in view that some subcategories are too similar to tell them apart easily, we fuse the subcategories iteratively according to their similarities, and learn fused one-vs-all features. Experimental results show the superior performance of our algorithms over the existing methods." @default.
- W2247349754 created "2016-06-24" @default.
- W2247349754 creator A5002494284 @default.
- W2247349754 creator A5007238584 @default.
- W2247349754 creator A5046805800 @default.
- W2247349754 creator A5047455588 @default.
- W2247349754 date "2016-02-01" @default.
- W2247349754 modified "2023-10-16" @default.
- W2247349754 title "Fused One-vs-All Features With Semantic Alignments for Fine-Grained Visual Categorization" @default.
- W2247349754 cites W1496650988 @default.
- W2247349754 cites W1975399404 @default.
- W2247349754 cites W1976921161 @default.
- W2247349754 cites W1977295328 @default.
- W2247349754 cites W1980526845 @default.
- W2247349754 cites W1982067089 @default.
- W2247349754 cites W1988898685 @default.
- W2247349754 cites W1989684337 @default.
- W2247349754 cites W1999758002 @default.
- W2247349754 cites W2014102544 @default.
- W2247349754 cites W2027922120 @default.
- W2247349754 cites W2031489346 @default.
- W2247349754 cites W2045798786 @default.
- W2247349754 cites W2049750909 @default.
- W2247349754 cites W2079789819 @default.
- W2247349754 cites W2088049833 @default.
- W2247349754 cites W2090042335 @default.
- W2247349754 cites W2102605133 @default.
- W2247349754 cites W2104371740 @default.
- W2247349754 cites W2110015572 @default.
- W2247349754 cites W2113080973 @default.
- W2247349754 cites W2118696714 @default.
- W2247349754 cites W2120419212 @default.
- W2247349754 cites W2135706578 @default.
- W2247349754 cites W2143516773 @default.
- W2247349754 cites W2151103935 @default.
- W2247349754 cites W2155490028 @default.
- W2247349754 cites W2159797991 @default.
- W2247349754 cites W2162915993 @default.
- W2247349754 cites W2167481535 @default.
- W2247349754 cites W3143107425 @default.
- W2247349754 doi "https://doi.org/10.1109/tip.2015.2509425" @default.
- W2247349754 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26685247" @default.
- W2247349754 hasPublicationYear "2016" @default.
- W2247349754 type Work @default.
- W2247349754 sameAs 2247349754 @default.
- W2247349754 citedByCount "32" @default.
- W2247349754 countsByYear W22473497542016 @default.
- W2247349754 countsByYear W22473497542017 @default.
- W2247349754 countsByYear W22473497542018 @default.
- W2247349754 countsByYear W22473497542019 @default.
- W2247349754 countsByYear W22473497542020 @default.
- W2247349754 countsByYear W22473497542021 @default.
- W2247349754 countsByYear W22473497542022 @default.
- W2247349754 countsByYear W22473497542023 @default.
- W2247349754 crossrefType "journal-article" @default.
- W2247349754 hasAuthorship W2247349754A5002494284 @default.
- W2247349754 hasAuthorship W2247349754A5007238584 @default.
- W2247349754 hasAuthorship W2247349754A5046805800 @default.
- W2247349754 hasAuthorship W2247349754A5047455588 @default.
- W2247349754 hasConcept C103278499 @default.
- W2247349754 hasConcept C105795698 @default.
- W2247349754 hasConcept C111472728 @default.
- W2247349754 hasConcept C115961682 @default.
- W2247349754 hasConcept C119599485 @default.
- W2247349754 hasConcept C127413603 @default.
- W2247349754 hasConcept C138885662 @default.
- W2247349754 hasConcept C141353440 @default.
- W2247349754 hasConcept C142575187 @default.
- W2247349754 hasConcept C153180895 @default.
- W2247349754 hasConcept C154945302 @default.
- W2247349754 hasConcept C165064840 @default.
- W2247349754 hasConcept C184337299 @default.
- W2247349754 hasConcept C199360897 @default.
- W2247349754 hasConcept C202444582 @default.
- W2247349754 hasConcept C2524010 @default.
- W2247349754 hasConcept C2777212361 @default.
- W2247349754 hasConcept C2780586882 @default.
- W2247349754 hasConcept C31972630 @default.
- W2247349754 hasConcept C33676613 @default.
- W2247349754 hasConcept C33923547 @default.
- W2247349754 hasConcept C36464697 @default.
- W2247349754 hasConcept C41008148 @default.
- W2247349754 hasConcept C52622490 @default.
- W2247349754 hasConcept C79337645 @default.
- W2247349754 hasConcept C94124525 @default.
- W2247349754 hasConcept C97931131 @default.
- W2247349754 hasConceptScore W2247349754C103278499 @default.
- W2247349754 hasConceptScore W2247349754C105795698 @default.
- W2247349754 hasConceptScore W2247349754C111472728 @default.
- W2247349754 hasConceptScore W2247349754C115961682 @default.
- W2247349754 hasConceptScore W2247349754C119599485 @default.
- W2247349754 hasConceptScore W2247349754C127413603 @default.
- W2247349754 hasConceptScore W2247349754C138885662 @default.
- W2247349754 hasConceptScore W2247349754C141353440 @default.
- W2247349754 hasConceptScore W2247349754C142575187 @default.
- W2247349754 hasConceptScore W2247349754C153180895 @default.
- W2247349754 hasConceptScore W2247349754C154945302 @default.
- W2247349754 hasConceptScore W2247349754C165064840 @default.