Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157485847> ?p ?o ?g. }
- W3157485847 endingPage "2045" @default.
- W3157485847 startingPage "2034" @default.
- W3157485847 abstract "Mixed dish is a food category that contains different dishes mixed in one plate, and is popular in Eastern and Southeast Asia. Recognizing the individual dishes in a mixed dish image is important for health related applications, e.g. to calculate the nutrition values of the dish. However, most existing methods that focus on single dish classification are not applicable to the recognition of mixed dish images. The main challenge of mixed dish recognition comes from three aspects: a wide range of dish types, the complex dish combination with severe overlap between different dishes and the large visual variances of same dish type caused by different cooking/cutting methods applied in different canteens. In order to tackle these problems, we propose the contextual relation network that encodes the implicit and explicit contextual relations among multiple dishes from region-level features and label-level co-occurrence respectively. Besides, to address the visual variances of dish instances from different canteens, we introduce the domain adaption networks to align both local and global features, and eliminating domain gaps of dish features across different canteens. In addition, we collect a mixed dish image dataset containing 9254 mixed dish images from 6 canteens in Singapore. Extensive experiments on both our dataset and public one validate that our methods can achieve top performance for localizing and recognizing multiple dishes and solve the domain shift problem to a certain extent in mixed dish images." @default.
- W3157485847 created "2021-05-10" @default.
- W3157485847 creator A5010722442 @default.
- W3157485847 creator A5034434932 @default.
- W3157485847 creator A5043522804 @default.
- W3157485847 creator A5046305086 @default.
- W3157485847 creator A5056776177 @default.
- W3157485847 creator A5058061332 @default.
- W3157485847 creator A5089404640 @default.
- W3157485847 date "2022-01-01" @default.
- W3157485847 modified "2023-10-16" @default.
- W3157485847 title "Mixed Dish Recognition With Contextual Relation and Domain Alignment" @default.
- W3157485847 cites W1030521295 @default.
- W3157485847 cites W12634471 @default.
- W3157485847 cites W1496513042 @default.
- W3157485847 cites W1964856489 @default.
- W3157485847 cites W1979008561 @default.
- W3157485847 cites W1982635469 @default.
- W3157485847 cites W2000105909 @default.
- W3157485847 cites W2007121115 @default.
- W3157485847 cites W2036989445 @default.
- W3157485847 cites W2096761622 @default.
- W3157485847 cites W2128053425 @default.
- W3157485847 cites W2130448385 @default.
- W3157485847 cites W2194775991 @default.
- W3157485847 cites W2206370378 @default.
- W3157485847 cites W2414162830 @default.
- W3157485847 cites W2526198870 @default.
- W3157485847 cites W2529459268 @default.
- W3157485847 cites W2530422462 @default.
- W3157485847 cites W2530542266 @default.
- W3157485847 cites W2531177272 @default.
- W3157485847 cites W2531603677 @default.
- W3157485847 cites W2535808783 @default.
- W3157485847 cites W2570343428 @default.
- W3157485847 cites W2583892095 @default.
- W3157485847 cites W2593414223 @default.
- W3157485847 cites W2593768305 @default.
- W3157485847 cites W2737449799 @default.
- W3157485847 cites W2738418280 @default.
- W3157485847 cites W2742792558 @default.
- W3157485847 cites W2765707332 @default.
- W3157485847 cites W2782829507 @default.
- W3157485847 cites W2824941129 @default.
- W3157485847 cites W2892022580 @default.
- W3157485847 cites W2903855512 @default.
- W3157485847 cites W2962901913 @default.
- W3157485847 cites W2963150697 @default.
- W3157485847 cites W2963217233 @default.
- W3157485847 cites W2963351448 @default.
- W3157485847 cites W2963556277 @default.
- W3157485847 cites W2964080601 @default.
- W3157485847 cites W2968634921 @default.
- W3157485847 cites W2981771452 @default.
- W3157485847 cites W3041485444 @default.
- W3157485847 cites W3048602385 @default.
- W3157485847 cites W3104226648 @default.
- W3157485847 cites W3108004548 @default.
- W3157485847 cites W3110070597 @default.
- W3157485847 cites W4293052541 @default.
- W3157485847 cites W639708223 @default.
- W3157485847 doi "https://doi.org/10.1109/tmm.2021.3075037" @default.
- W3157485847 hasPublicationYear "2022" @default.
- W3157485847 type Work @default.
- W3157485847 sameAs 3157485847 @default.
- W3157485847 citedByCount "5" @default.
- W3157485847 countsByYear W31574858472021 @default.
- W3157485847 countsByYear W31574858472022 @default.
- W3157485847 countsByYear W31574858472023 @default.
- W3157485847 crossrefType "journal-article" @default.
- W3157485847 hasAuthorship W3157485847A5010722442 @default.
- W3157485847 hasAuthorship W3157485847A5034434932 @default.
- W3157485847 hasAuthorship W3157485847A5043522804 @default.
- W3157485847 hasAuthorship W3157485847A5046305086 @default.
- W3157485847 hasAuthorship W3157485847A5056776177 @default.
- W3157485847 hasAuthorship W3157485847A5058061332 @default.
- W3157485847 hasAuthorship W3157485847A5089404640 @default.
- W3157485847 hasBestOaLocation W31574858472 @default.
- W3157485847 hasConcept C120665830 @default.
- W3157485847 hasConcept C121332964 @default.
- W3157485847 hasConcept C124101348 @default.
- W3157485847 hasConcept C134306372 @default.
- W3157485847 hasConcept C154945302 @default.
- W3157485847 hasConcept C192209626 @default.
- W3157485847 hasConcept C25343380 @default.
- W3157485847 hasConcept C31972630 @default.
- W3157485847 hasConcept C33923547 @default.
- W3157485847 hasConcept C36503486 @default.
- W3157485847 hasConcept C41008148 @default.
- W3157485847 hasConceptScore W3157485847C120665830 @default.
- W3157485847 hasConceptScore W3157485847C121332964 @default.
- W3157485847 hasConceptScore W3157485847C124101348 @default.
- W3157485847 hasConceptScore W3157485847C134306372 @default.
- W3157485847 hasConceptScore W3157485847C154945302 @default.
- W3157485847 hasConceptScore W3157485847C192209626 @default.
- W3157485847 hasConceptScore W3157485847C25343380 @default.
- W3157485847 hasConceptScore W3157485847C31972630 @default.
- W3157485847 hasConceptScore W3157485847C33923547 @default.