Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949676865> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2949676865 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.
- W2949676865 created "2019-06-27" @default.
- W2949676865 creator A5054137460 @default.
- W2949676865 creator A5088559134 @default.
- W2949676865 date "2015-12-08" @default.
- W2949676865 modified "2023-09-27" @default.
- W2949676865 title "Fine-grained Image Classification by Exploring Bipartite-Graph Labels" @default.
- W2949676865 cites W1797268635 @default.
- W2949676865 cites W2021354639 @default.
- W2949676865 cites W2039507552 @default.
- W2949676865 cites W2055527244 @default.
- W2949676865 cites W2110015572 @default.
- W2949676865 cites W2913340405 @default.
- W2949676865 cites W2950094539 @default.
- W2949676865 cites W2964176323 @default.
- W2949676865 cites W603908379 @default.
- W2949676865 doi "https://doi.org/10.48550/arxiv.1512.02665" @default.
- W2949676865 hasPublicationYear "2015" @default.
- W2949676865 type Work @default.
- W2949676865 sameAs 2949676865 @default.
- W2949676865 citedByCount "1" @default.
- W2949676865 countsByYear W29496768652017 @default.
- W2949676865 crossrefType "posted-content" @default.
- W2949676865 hasAuthorship W2949676865A5054137460 @default.
- W2949676865 hasAuthorship W2949676865A5088559134 @default.
- W2949676865 hasBestOaLocation W29496768651 @default.
- W2949676865 hasConcept C111919701 @default.
- W2949676865 hasConcept C119857082 @default.
- W2949676865 hasConcept C132525143 @default.
- W2949676865 hasConcept C153180895 @default.
- W2949676865 hasConcept C154945302 @default.
- W2949676865 hasConcept C165696696 @default.
- W2949676865 hasConcept C177774035 @default.
- W2949676865 hasConcept C185798385 @default.
- W2949676865 hasConcept C197657726 @default.
- W2949676865 hasConcept C205649164 @default.
- W2949676865 hasConcept C2776214188 @default.
- W2949676865 hasConcept C38652104 @default.
- W2949676865 hasConcept C41008148 @default.
- W2949676865 hasConcept C58640448 @default.
- W2949676865 hasConcept C80444323 @default.
- W2949676865 hasConcept C81363708 @default.
- W2949676865 hasConceptScore W2949676865C111919701 @default.
- W2949676865 hasConceptScore W2949676865C119857082 @default.
- W2949676865 hasConceptScore W2949676865C132525143 @default.
- W2949676865 hasConceptScore W2949676865C153180895 @default.
- W2949676865 hasConceptScore W2949676865C154945302 @default.
- W2949676865 hasConceptScore W2949676865C165696696 @default.
- W2949676865 hasConceptScore W2949676865C177774035 @default.
- W2949676865 hasConceptScore W2949676865C185798385 @default.
- W2949676865 hasConceptScore W2949676865C197657726 @default.
- W2949676865 hasConceptScore W2949676865C205649164 @default.
- W2949676865 hasConceptScore W2949676865C2776214188 @default.
- W2949676865 hasConceptScore W2949676865C38652104 @default.
- W2949676865 hasConceptScore W2949676865C41008148 @default.
- W2949676865 hasConceptScore W2949676865C58640448 @default.
- W2949676865 hasConceptScore W2949676865C80444323 @default.
- W2949676865 hasConceptScore W2949676865C81363708 @default.
- W2949676865 hasLocation W29496768651 @default.
- W2949676865 hasLocation W29496768652 @default.
- W2949676865 hasOpenAccess W2949676865 @default.
- W2949676865 hasPrimaryLocation W29496768651 @default.
- W2949676865 hasRelatedWork W2355108509 @default.
- W2949676865 hasRelatedWork W2767651786 @default.
- W2949676865 hasRelatedWork W2912288872 @default.
- W2949676865 hasRelatedWork W3021430260 @default.
- W2949676865 hasRelatedWork W3027997911 @default.
- W2949676865 hasRelatedWork W3081278020 @default.
- W2949676865 hasRelatedWork W3208185614 @default.
- W2949676865 hasRelatedWork W4287776258 @default.
- W2949676865 hasRelatedWork W4297899248 @default.
- W2949676865 hasRelatedWork W564581980 @default.
- W2949676865 isParatext "false" @default.
- W2949676865 isRetracted "false" @default.
- W2949676865 magId "2949676865" @default.
- W2949676865 workType "article" @default.