FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765268259> ?p ?o ?g. }

• W2765268259 endingPage "1500" @default.
• W2765268259 startingPage "1487" @default.
• W2765268259 abstract "Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category, such as 200 subcategories belonging to the bird, which is highly challenging due to large variance in the same subcategory and small variance among different subcategories. Existing methods generally first locate the objects or parts and then discriminate which subcategory the image belongs to. However, they mainly have two limitations: 1) relying on object or part annotations which are heavily labor consuming; and 2) ignoring the spatial relationships between the object and its parts as well as among these parts, both of which are significantly helpful for finding discriminative parts. Therefore, this paper proposes the object-part attention model (OPAM) for weakly supervised fine-grained image classification and the main novelties are: 1) object-part attention model integrates two level attentions: object-level attention localizes objects of images, and part-level attention selects discriminative parts of object. Both are jointly employed to learn multi-view and multi-scale features to enhance their mutual promotion; and 2) Object-part spatial constraint model combines two spatial constraints: object spatial constraint ensures selected parts highly representative and part spatial constraint eliminates redundancy and enhances discrimination of selected parts. Both are jointly employed to exploit the subtle and local differences for distinguishing the subcategories. Importantly, neither object nor part annotations are used in our proposed approach, which avoids the heavy labor consumption of labeling. Compared with more than ten state-of-the-art methods on four widely-used datasets, our OPAM approach achieves the best performance." @default.
• W2765268259 created "2017-11-10" @default.
• W2765268259 creator A5047811387 @default.
• W2765268259 creator A5060500814 @default.
• W2765268259 date "2018-03-01" @default.
• W2765268259 modified "2023-10-16" @default.
• W2765268259 title "Object-Part Attention Model for Fine-Grained Image Classification" @default.
• W2765268259 cites W1496650988 @default.
• W2765268259 cites W166750225 @default.
• W2765268259 cites W1898560071 @default.
• W2765268259 cites W1920702274 @default.
• W2765268259 cites W1929903369 @default.
• W2765268259 cites W1955942245 @default.
• W2765268259 cites W1977295328 @default.
• W2765268259 cites W1980526845 @default.
• W2765268259 cites W1982067089 @default.
• W2765268259 cites W1988898685 @default.
• W2765268259 cites W2027922120 @default.
• W2765268259 cites W2038752770 @default.
• W2765268259 cites W2062118960 @default.
• W2765268259 cites W2068562306 @default.
• W2765268259 cites W2079789819 @default.
• W2765268259 cites W2088049833 @default.
• W2765268259 cites W2097117768 @default.
• W2765268259 cites W2102605133 @default.
• W2765268259 cites W2104371740 @default.
• W2765268259 cites W2104657103 @default.
• W2765268259 cites W2110015572 @default.
• W2765268259 cites W2118696714 @default.
• W2765268259 cites W2138011018 @default.
• W2765268259 cites W2151103935 @default.
• W2765268259 cites W2155839910 @default.
• W2765268259 cites W2194011657 @default.
• W2765268259 cites W2202499615 @default.
• W2765268259 cites W2207849498 @default.
• W2765268259 cites W2211589372 @default.
• W2765268259 cites W2247349754 @default.
• W2765268259 cites W2289708887 @default.
• W2765268259 cites W2295107390 @default.
• W2765268259 cites W2345500696 @default.
• W2765268259 cites W2462457117 @default.
• W2765268259 cites W2479109623 @default.
• W2765268259 cites W2515116636 @default.
• W2765268259 cites W2533598788 @default.
• W2765268259 cites W2544405876 @default.
• W2765268259 cites W2555741539 @default.
• W2765268259 cites W2558914813 @default.
• W2765268259 cites W2560552919 @default.
• W2765268259 cites W2579318141 @default.
• W2765268259 cites W2962798895 @default.
• W2765268259 cites W2964036919 @default.
• W2765268259 cites W2964176323 @default.
• W2765268259 cites W3124951096 @default.
• W2765268259 cites W56385144 @default.
• W2765268259 doi "https://doi.org/10.1109/tip.2017.2774041" @default.
• W2765268259 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29990123" @default.
• W2765268259 hasPublicationYear "2018" @default.
• W2765268259 type Work @default.
• W2765268259 sameAs 2765268259 @default.
• W2765268259 citedByCount "273" @default.
• W2765268259 countsByYear W27652682592018 @default.
• W2765268259 countsByYear W27652682592019 @default.
• W2765268259 countsByYear W27652682592020 @default.
• W2765268259 countsByYear W27652682592021 @default.
• W2765268259 countsByYear W27652682592022 @default.
• W2765268259 countsByYear W27652682592023 @default.
• W2765268259 crossrefType "journal-article" @default.
• W2765268259 hasAuthorship W2765268259A5047811387 @default.
• W2765268259 hasAuthorship W2765268259A5060500814 @default.
• W2765268259 hasBestOaLocation W27652682592 @default.
• W2765268259 hasConcept C111919701 @default.
• W2765268259 hasConcept C115961682 @default.
• W2765268259 hasConcept C119857082 @default.
• W2765268259 hasConcept C152124472 @default.
• W2765268259 hasConcept C153180895 @default.
• W2765268259 hasConcept C154945302 @default.
• W2765268259 hasConcept C202444582 @default.
• W2765268259 hasConcept C2524010 @default.
• W2765268259 hasConcept C2776036281 @default.
• W2765268259 hasConcept C2776151529 @default.
• W2765268259 hasConcept C2780617661 @default.
• W2765268259 hasConcept C2781238097 @default.
• W2765268259 hasConcept C31972630 @default.
• W2765268259 hasConcept C33923547 @default.
• W2765268259 hasConcept C41008148 @default.
• W2765268259 hasConcept C75294576 @default.
• W2765268259 hasConcept C97931131 @default.
• W2765268259 hasConceptScore W2765268259C111919701 @default.
• W2765268259 hasConceptScore W2765268259C115961682 @default.
• W2765268259 hasConceptScore W2765268259C119857082 @default.
• W2765268259 hasConceptScore W2765268259C152124472 @default.
• W2765268259 hasConceptScore W2765268259C153180895 @default.
• W2765268259 hasConceptScore W2765268259C154945302 @default.
• W2765268259 hasConceptScore W2765268259C202444582 @default.
• W2765268259 hasConceptScore W2765268259C2524010 @default.
• W2765268259 hasConceptScore W2765268259C2776036281 @default.
• W2765268259 hasConceptScore W2765268259C2776151529 @default.
• W2765268259 hasConceptScore W2765268259C2780617661 @default.

• next