Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098055474> ?p ?o ?g. }
- W3098055474 endingPage "4755" @default.
- W3098055474 startingPage "4740" @default.
- W3098055474 abstract "In this paper, a level-wise mixture model (LMM) is developed by embedding visual hierarchy with deep networks to support large-scale visual recognition (i.e., recognizing thousands or even tens of thousands of object classes), and a Bayesian approach is used to adapt a pre-trained visual hierarchy automatically to the improvements of deep features (that are used for image and object class representation) when more representative deep networks are learned along the time. Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative deep features for image and object class representation; (b) the tree classifier for recognizing large numbers of object classes hierarchically; and (c) the visual hierarchy adaptation for achieving more accurate indexing of large numbers of object classes hierarchically. By supporting joint learning of the tree classifier, the deep networks and the visual hierarchy adaptation, our LMM algorithm can provide an effective approach for controlling inter-level error propagation effectively, thus it can achieve better accuracy rates on large-scale visual recognition. Our experiments are carried on ImageNet1K and ImageNet10K image sets, and our LMM algorithm can achieve very competitive results on both the accuracy rates and the computation efficiency as compared with the baseline methods." @default.
- W3098055474 created "2020-11-23" @default.
- W3098055474 creator A5038291633 @default.
- W3098055474 creator A5039849966 @default.
- W3098055474 creator A5043447052 @default.
- W3098055474 creator A5049381658 @default.
- W3098055474 creator A5051004995 @default.
- W3098055474 creator A5054557971 @default.
- W3098055474 creator A5063145868 @default.
- W3098055474 date "2018-10-01" @default.
- W3098055474 modified "2023-10-11" @default.
- W3098055474 title "Embedding Visual Hierarchy With Deep Networks for Large-Scale Visual Recognition" @default.
- W3098055474 cites W114517082 @default.
- W3098055474 cites W1851597118 @default.
- W3098055474 cites W1896424170 @default.
- W3098055474 cites W1948751323 @default.
- W3098055474 cites W1959000896 @default.
- W3098055474 cites W1967732418 @default.
- W3098055474 cites W1970719635 @default.
- W3098055474 cites W1987083125 @default.
- W3098055474 cites W2008835805 @default.
- W3098055474 cites W2017637319 @default.
- W3098055474 cites W2052678124 @default.
- W3098055474 cites W2069682406 @default.
- W3098055474 cites W2089150756 @default.
- W3098055474 cites W2091759811 @default.
- W3098055474 cites W2097117768 @default.
- W3098055474 cites W2098020658 @default.
- W3098055474 cites W2101722384 @default.
- W3098055474 cites W2106097867 @default.
- W3098055474 cites W2108598243 @default.
- W3098055474 cites W2109256565 @default.
- W3098055474 cites W2110765924 @default.
- W3098055474 cites W2112796928 @default.
- W3098055474 cites W2112993448 @default.
- W3098055474 cites W2113120414 @default.
- W3098055474 cites W2116339064 @default.
- W3098055474 cites W2120725344 @default.
- W3098055474 cites W2122146326 @default.
- W3098055474 cites W2128017662 @default.
- W3098055474 cites W2128154306 @default.
- W3098055474 cites W2134665698 @default.
- W3098055474 cites W2138516811 @default.
- W3098055474 cites W2142747154 @default.
- W3098055474 cites W2147347517 @default.
- W3098055474 cites W2148780922 @default.
- W3098055474 cites W2152923755 @default.
- W3098055474 cites W2154624311 @default.
- W3098055474 cites W2194775991 @default.
- W3098055474 cites W2220384803 @default.
- W3098055474 cites W2321627895 @default.
- W3098055474 cites W2480418144 @default.
- W3098055474 cites W2507855991 @default.
- W3098055474 cites W2511374729 @default.
- W3098055474 cites W2568998735 @default.
- W3098055474 cites W2586505867 @default.
- W3098055474 cites W2605809234 @default.
- W3098055474 cites W2962992847 @default.
- W3098055474 cites W64813323 @default.
- W3098055474 cites W1981998038 @default.
- W3098055474 doi "https://doi.org/10.1109/tip.2018.2845118" @default.
- W3098055474 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29994211" @default.
- W3098055474 hasPublicationYear "2018" @default.
- W3098055474 type Work @default.
- W3098055474 sameAs 3098055474 @default.
- W3098055474 citedByCount "25" @default.
- W3098055474 countsByYear W30980554742019 @default.
- W3098055474 countsByYear W30980554742020 @default.
- W3098055474 countsByYear W30980554742021 @default.
- W3098055474 countsByYear W30980554742022 @default.
- W3098055474 countsByYear W30980554742023 @default.
- W3098055474 crossrefType "journal-article" @default.
- W3098055474 hasAuthorship W3098055474A5038291633 @default.
- W3098055474 hasAuthorship W3098055474A5039849966 @default.
- W3098055474 hasAuthorship W3098055474A5043447052 @default.
- W3098055474 hasAuthorship W3098055474A5049381658 @default.
- W3098055474 hasAuthorship W3098055474A5051004995 @default.
- W3098055474 hasAuthorship W3098055474A5054557971 @default.
- W3098055474 hasAuthorship W3098055474A5063145868 @default.
- W3098055474 hasBestOaLocation W30980554741 @default.
- W3098055474 hasConcept C108583219 @default.
- W3098055474 hasConcept C115961682 @default.
- W3098055474 hasConcept C119857082 @default.
- W3098055474 hasConcept C153180895 @default.
- W3098055474 hasConcept C154945302 @default.
- W3098055474 hasConcept C2776151529 @default.
- W3098055474 hasConcept C36464697 @default.
- W3098055474 hasConcept C41008148 @default.
- W3098055474 hasConcept C41608201 @default.
- W3098055474 hasConcept C52622490 @default.
- W3098055474 hasConcept C64876066 @default.
- W3098055474 hasConcept C75294576 @default.
- W3098055474 hasConcept C95623464 @default.
- W3098055474 hasConcept C97931131 @default.
- W3098055474 hasConceptScore W3098055474C108583219 @default.
- W3098055474 hasConceptScore W3098055474C115961682 @default.
- W3098055474 hasConceptScore W3098055474C119857082 @default.
- W3098055474 hasConceptScore W3098055474C153180895 @default.