Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310244111> ?p ?o ?g. }
- W4310244111 endingPage "103159" @default.
- W4310244111 startingPage "103159" @default.
- W4310244111 abstract "With the development of 3D technology and the increase in 3D models, 2D image-based 3D model retrieval tasks have drawn increased attention from scholars. Previous works align cross-domain features via adversarial domain alignment and semantic alignment. However, the extracted features of previous methods are disturbed by the residual domain-specific features, and the lack of labels for 3D models makes the semantic alignment challenging. Therefore, we propose disentangled feature learning associated with enhanced semantic alignment to address these problems. On one hand, the disentangled feature learning enables decoupling the twisted raw features into the isolated domain-invariant and domain-specific features, and the domain-specific features will be dropped while performing adversarial domain alignment and semantic alignment to acquire domain-invariant features. On the other hand, we mine the semantic consistency by compacting each 3D model sample and its nearest neighbors to further enhance semantic alignment for unlabeled 3D model domain. We give comprehensive experiments on two public datasets, and the results demonstrate the superiority of the proposed method. Especially on MI3DOR-2 dataset, our method outperforms the current state-of-the-art methods with gains of 2.88% for the strictest retrieval metric NN." @default.
- W4310244111 created "2022-11-30" @default.
- W4310244111 creator A5029756519 @default.
- W4310244111 creator A5032859417 @default.
- W4310244111 creator A5058652390 @default.
- W4310244111 creator A5063675255 @default.
- W4310244111 creator A5074077175 @default.
- W4310244111 creator A5088174174 @default.
- W4310244111 date "2023-03-01" @default.
- W4310244111 modified "2023-10-09" @default.
- W4310244111 title "Image-based 3D model retrieval via disentangled feature learning and enhanced semantic alignment" @default.
- W4310244111 cites W1644641054 @default.
- W4310244111 cites W1972969301 @default.
- W4310244111 cites W2104068492 @default.
- W4310244111 cites W2122585444 @default.
- W4310244111 cites W2194775991 @default.
- W4310244111 cites W2328765253 @default.
- W4310244111 cites W2593768305 @default.
- W4310244111 cites W2616287544 @default.
- W4310244111 cites W2749056374 @default.
- W4310244111 cites W2779039928 @default.
- W4310244111 cites W2790362762 @default.
- W4310244111 cites W2798984401 @default.
- W4310244111 cites W2799162093 @default.
- W4310244111 cites W2808170586 @default.
- W4310244111 cites W2810981979 @default.
- W4310244111 cites W2896196878 @default.
- W4310244111 cites W2902078856 @default.
- W4310244111 cites W2912849458 @default.
- W4310244111 cites W2963231572 @default.
- W4310244111 cites W2963275094 @default.
- W4310244111 cites W2963789515 @default.
- W4310244111 cites W2979750740 @default.
- W4310244111 cites W2981506675 @default.
- W4310244111 cites W2997189783 @default.
- W4310244111 cites W2998043922 @default.
- W4310244111 cites W3007132505 @default.
- W4310244111 cites W3009238340 @default.
- W4310244111 cites W3025994431 @default.
- W4310244111 cites W3034478348 @default.
- W4310244111 cites W3034591020 @default.
- W4310244111 cites W3036301695 @default.
- W4310244111 cites W3076174210 @default.
- W4310244111 cites W3093133634 @default.
- W4310244111 cites W3107670916 @default.
- W4310244111 cites W3109137304 @default.
- W4310244111 cites W3168718178 @default.
- W4310244111 cites W3176372702 @default.
- W4310244111 cites W3196335228 @default.
- W4310244111 cites W4207018409 @default.
- W4310244111 cites W4226137223 @default.
- W4310244111 cites W4285130696 @default.
- W4310244111 cites W4287124998 @default.
- W4310244111 cites W4312792979 @default.
- W4310244111 doi "https://doi.org/10.1016/j.ipm.2022.103159" @default.
- W4310244111 hasPublicationYear "2023" @default.
- W4310244111 type Work @default.
- W4310244111 citedByCount "1" @default.
- W4310244111 countsByYear W43102441112023 @default.
- W4310244111 crossrefType "journal-article" @default.
- W4310244111 hasAuthorship W4310244111A5029756519 @default.
- W4310244111 hasAuthorship W4310244111A5032859417 @default.
- W4310244111 hasAuthorship W4310244111A5058652390 @default.
- W4310244111 hasAuthorship W4310244111A5063675255 @default.
- W4310244111 hasAuthorship W4310244111A5074077175 @default.
- W4310244111 hasAuthorship W4310244111A5088174174 @default.
- W4310244111 hasConcept C11413529 @default.
- W4310244111 hasConcept C115961682 @default.
- W4310244111 hasConcept C119857082 @default.
- W4310244111 hasConcept C134306372 @default.
- W4310244111 hasConcept C138885662 @default.
- W4310244111 hasConcept C153180895 @default.
- W4310244111 hasConcept C154945302 @default.
- W4310244111 hasConcept C155512373 @default.
- W4310244111 hasConcept C162324750 @default.
- W4310244111 hasConcept C1667742 @default.
- W4310244111 hasConcept C176217482 @default.
- W4310244111 hasConcept C21547014 @default.
- W4310244111 hasConcept C23123220 @default.
- W4310244111 hasConcept C2776401178 @default.
- W4310244111 hasConcept C2776436953 @default.
- W4310244111 hasConcept C33923547 @default.
- W4310244111 hasConcept C36503486 @default.
- W4310244111 hasConcept C41008148 @default.
- W4310244111 hasConcept C41895202 @default.
- W4310244111 hasConceptScore W4310244111C11413529 @default.
- W4310244111 hasConceptScore W4310244111C115961682 @default.
- W4310244111 hasConceptScore W4310244111C119857082 @default.
- W4310244111 hasConceptScore W4310244111C134306372 @default.
- W4310244111 hasConceptScore W4310244111C138885662 @default.
- W4310244111 hasConceptScore W4310244111C153180895 @default.
- W4310244111 hasConceptScore W4310244111C154945302 @default.
- W4310244111 hasConceptScore W4310244111C155512373 @default.
- W4310244111 hasConceptScore W4310244111C162324750 @default.
- W4310244111 hasConceptScore W4310244111C1667742 @default.
- W4310244111 hasConceptScore W4310244111C176217482 @default.
- W4310244111 hasConceptScore W4310244111C21547014 @default.
- W4310244111 hasConceptScore W4310244111C23123220 @default.