Matches in SemOpenAlex for { <https://semopenalex.org/work/W2194011657> ?p ?o ?g. }
- W2194011657 abstract "Given a food image, can a fine-grained object recognition engine tell which restaurant which dish the food belongs to? Such ultra-fine grained image recognition is the key for many applications like search by images, but it is very challenging because it needs to discern subtle difference between classes while dealing with the scarcity of training data. Fortunately, the ultra-fine granularity naturally brings rich relationships among object classes. This paper proposes a novel approach to exploit the rich relationships through bipartite-graph labels (BGL). We show how to model BGL in an overall convolutional neural networks and the resulting system can be optimized through back-propagation. We also show that it is computationally efficient in inference thanks to the bipartite structure. To facilitate the study, we construct a new food benchmark dataset, which consists of 37,885 food images collected from 6 restaurants and totally 975 menus. Experimental results on this new food and three other datasets demonstrates BGL advances previous works in fine-grained object recognition. An online demo is available at http://www.f-zhou.com/fg_demo/." @default.
- W2194011657 created "2016-06-24" @default.
- W2194011657 creator A5054137460 @default.
- W2194011657 creator A5088559134 @default.
- W2194011657 date "2016-06-01" @default.
- W2194011657 modified "2023-10-14" @default.
- W2194011657 title "Fine-Grained Image Classification by Exploring Bipartite-Graph Labels" @default.
- W2194011657 cites W1677182931 @default.
- W2194011657 cites W1898560071 @default.
- W2194011657 cites W1929903369 @default.
- W2194011657 cites W1972939083 @default.
- W2194011657 cites W1975517671 @default.
- W2194011657 cites W1977295328 @default.
- W2194011657 cites W1993309459 @default.
- W2194011657 cites W1995543189 @default.
- W2194011657 cites W2000105909 @default.
- W2194011657 cites W2021354639 @default.
- W2194011657 cites W2037227137 @default.
- W2194011657 cites W2039507552 @default.
- W2194011657 cites W2045750950 @default.
- W2194011657 cites W2079479194 @default.
- W2194011657 cites W2079789819 @default.
- W2194011657 cites W2091759811 @default.
- W2194011657 cites W2093848332 @default.
- W2194011657 cites W2101722384 @default.
- W2194011657 cites W2104657103 @default.
- W2194011657 cites W2110015572 @default.
- W2194011657 cites W2110226160 @default.
- W2194011657 cites W2110765924 @default.
- W2194011657 cites W2117030034 @default.
- W2194011657 cites W2126448884 @default.
- W2194011657 cites W2138011018 @default.
- W2194011657 cites W2143104527 @default.
- W2194011657 cites W2147414309 @default.
- W2194011657 cites W2148141637 @default.
- W2194011657 cites W2148780922 @default.
- W2194011657 cites W2155839910 @default.
- W2194011657 cites W2171671655 @default.
- W2194011657 cites W2200019946 @default.
- W2194011657 cites W2205343627 @default.
- W2194011657 cites W2206370378 @default.
- W2194011657 cites W2294130536 @default.
- W2194011657 cites W2533598788 @default.
- W2194011657 cites W2913340405 @default.
- W2194011657 cites W2964176323 @default.
- W2194011657 cites W3143107425 @default.
- W2194011657 doi "https://doi.org/10.1109/cvpr.2016.127" @default.
- W2194011657 hasPublicationYear "2016" @default.
- W2194011657 type Work @default.
- W2194011657 sameAs 2194011657 @default.
- W2194011657 citedByCount "93" @default.
- W2194011657 countsByYear W21940116572016 @default.
- W2194011657 countsByYear W21940116572017 @default.
- W2194011657 countsByYear W21940116572018 @default.
- W2194011657 countsByYear W21940116572019 @default.
- W2194011657 countsByYear W21940116572020 @default.
- W2194011657 countsByYear W21940116572021 @default.
- W2194011657 countsByYear W21940116572022 @default.
- W2194011657 countsByYear W21940116572023 @default.
- W2194011657 crossrefType "proceedings-article" @default.
- W2194011657 hasAuthorship W2194011657A5054137460 @default.
- W2194011657 hasAuthorship W2194011657A5088559134 @default.
- W2194011657 hasBestOaLocation W21940116572 @default.
- W2194011657 hasConcept C111919701 @default.
- W2194011657 hasConcept C119857082 @default.
- W2194011657 hasConcept C132525143 @default.
- W2194011657 hasConcept C13280743 @default.
- W2194011657 hasConcept C153180895 @default.
- W2194011657 hasConcept C154945302 @default.
- W2194011657 hasConcept C165696696 @default.
- W2194011657 hasConcept C177774035 @default.
- W2194011657 hasConcept C185798385 @default.
- W2194011657 hasConcept C197657726 @default.
- W2194011657 hasConcept C205649164 @default.
- W2194011657 hasConcept C2776214188 @default.
- W2194011657 hasConcept C2781238097 @default.
- W2194011657 hasConcept C38652104 @default.
- W2194011657 hasConcept C41008148 @default.
- W2194011657 hasConcept C64876066 @default.
- W2194011657 hasConcept C80444323 @default.
- W2194011657 hasConcept C81363708 @default.
- W2194011657 hasConceptScore W2194011657C111919701 @default.
- W2194011657 hasConceptScore W2194011657C119857082 @default.
- W2194011657 hasConceptScore W2194011657C132525143 @default.
- W2194011657 hasConceptScore W2194011657C13280743 @default.
- W2194011657 hasConceptScore W2194011657C153180895 @default.
- W2194011657 hasConceptScore W2194011657C154945302 @default.
- W2194011657 hasConceptScore W2194011657C165696696 @default.
- W2194011657 hasConceptScore W2194011657C177774035 @default.
- W2194011657 hasConceptScore W2194011657C185798385 @default.
- W2194011657 hasConceptScore W2194011657C197657726 @default.
- W2194011657 hasConceptScore W2194011657C205649164 @default.
- W2194011657 hasConceptScore W2194011657C2776214188 @default.
- W2194011657 hasConceptScore W2194011657C2781238097 @default.
- W2194011657 hasConceptScore W2194011657C38652104 @default.
- W2194011657 hasConceptScore W2194011657C41008148 @default.
- W2194011657 hasConceptScore W2194011657C64876066 @default.
- W2194011657 hasConceptScore W2194011657C80444323 @default.
- W2194011657 hasConceptScore W2194011657C81363708 @default.
- W2194011657 hasLocation W21940116571 @default.