FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947372468> ?p ?o ?g. }

• W2947372468 endingPage "3204" @default.
• W2947372468 startingPage "3194" @default.
• W2947372468 abstract "Intuitively, we can think of object recognition and attribute prediction as correlated tasks. However, they appeared to conflict in a simple two-branch multi-task framework (a category branch and an attribute branch) with a shared backbone part (convolutional layers and pooling layers). The performance dropped along with the iterative training steps. This result might have been caused by the noncoherent feature distribution between the object recognition features and the attribute prediction features. Recognition features are discriminative for different categories and are not sensitive to intracategory variations, while attribute prediction features are discriminative for different attributes, although these attributes can exist in objects from the same category. Thus, a conflict occurs when we force the network to learn the two kinds of distinct features simultaneously. To address this problem, we propose the category and attribute prediction network (CAP-net), in which a category-constrained attribute prediction structure is introduced to transfer the object recognition knowledge and avoid the conflict between two features. The CAP-net parameters can be learned easily with a regularization method. Extensive experimental results show that the CAP-net outperforms the state-of-the-art methods on object recognition and attribute prediction tasks." @default.
• W2947372468 created "2019-06-07" @default.
• W2947372468 creator A5005456828 @default.
• W2947372468 creator A5015744133 @default.
• W2947372468 creator A5043954827 @default.
• W2947372468 creator A5081388259 @default.
• W2947372468 date "2019-12-01" @default.
• W2947372468 modified "2023-09-25" @default.
• W2947372468 title "Can Categories and Attributes Be Learned in a Multi-Task Way?" @default.
• W2947372468 cites W113857012 @default.
• W2947372468 cites W1536680647 @default.
• W2947372468 cites W1574283247 @default.
• W2947372468 cites W1896424170 @default.
• W2947372468 cites W1900086069 @default.
• W2947372468 cites W1954735160 @default.
• W2947372468 cites W1962025484 @default.
• W2947372468 cites W1980526845 @default.
• W2947372468 cites W1981333244 @default.
• W2947372468 cites W1995543189 @default.
• W2947372468 cites W1999818274 @default.
• W2947372468 cites W2040171755 @default.
• W2947372468 cites W2055600015 @default.
• W2947372468 cites W206659046 @default.
• W2947372468 cites W2077656151 @default.
• W2947372468 cites W2088227600 @default.
• W2947372468 cites W2097117768 @default.
• W2947372468 cites W2098411764 @default.
• W2947372468 cites W2109317801 @default.
• W2947372468 cites W2117539524 @default.
• W2947372468 cites W2118696714 @default.
• W2947372468 cites W2122528955 @default.
• W2947372468 cites W2128532956 @default.
• W2947372468 cites W2135706578 @default.
• W2947372468 cites W2143104527 @default.
• W2947372468 cites W2147800946 @default.
• W2947372468 cites W2157423479 @default.
• W2947372468 cites W2183341477 @default.
• W2947372468 cites W2194775991 @default.
• W2947372468 cites W2201155408 @default.
• W2947372468 cites W2201936386 @default.
• W2947372468 cites W2216125271 @default.
• W2947372468 cites W2289324734 @default.
• W2947372468 cites W2346746376 @default.
• W2947372468 cites W2499554887 @default.
• W2947372468 cites W2520762063 @default.
• W2947372468 cites W2582553469 @default.
• W2947372468 cites W2605649771 @default.
• W2947372468 cites W2732937366 @default.
• W2947372468 cites W2755005384 @default.
• W2947372468 cites W2791217700 @default.
• W2947372468 cites W2890718122 @default.
• W2947372468 cites W2962716320 @default.
• W2947372468 cites W2963090248 @default.
• W2947372468 cites W2963150697 @default.
• W2947372468 cites W2963328724 @default.
• W2947372468 cites W2963377935 @default.
• W2947372468 cites W2963465381 @default.
• W2947372468 cites W2963650529 @default.
• W2947372468 cites W2963877604 @default.
• W2947372468 cites W2964248351 @default.
• W2947372468 cites W3100093508 @default.
• W2947372468 cites W3102668440 @default.
• W2947372468 cites W3103850820 @default.
• W2947372468 cites W3124951096 @default.
• W2947372468 cites W3143107425 @default.
• W2947372468 cites W56385144 @default.
• W2947372468 cites W639708223 @default.
• W2947372468 doi "https://doi.org/10.1109/tmm.2019.2919469" @default.
• W2947372468 hasPublicationYear "2019" @default.
• W2947372468 type Work @default.
• W2947372468 sameAs 2947372468 @default.
• W2947372468 citedByCount "4" @default.
• W2947372468 countsByYear W29473724682021 @default.
• W2947372468 countsByYear W29473724682022 @default.
• W2947372468 countsByYear W29473724682023 @default.
• W2947372468 crossrefType "journal-article" @default.
• W2947372468 hasAuthorship W2947372468A5005456828 @default.
• W2947372468 hasAuthorship W2947372468A5015744133 @default.
• W2947372468 hasAuthorship W2947372468A5043954827 @default.
• W2947372468 hasAuthorship W2947372468A5081388259 @default.
• W2947372468 hasConcept C119857082 @default.
• W2947372468 hasConcept C138885662 @default.
• W2947372468 hasConcept C153180895 @default.
• W2947372468 hasConcept C154945302 @default.
• W2947372468 hasConcept C162324750 @default.
• W2947372468 hasConcept C175154964 @default.
• W2947372468 hasConcept C187736073 @default.
• W2947372468 hasConcept C2776401178 @default.
• W2947372468 hasConcept C2780451532 @default.
• W2947372468 hasConcept C2781238097 @default.
• W2947372468 hasConcept C41008148 @default.
• W2947372468 hasConcept C41895202 @default.
• W2947372468 hasConcept C64876066 @default.
• W2947372468 hasConcept C70437156 @default.
• W2947372468 hasConcept C81363708 @default.
• W2947372468 hasConcept C97931131 @default.
• W2947372468 hasConceptScore W2947372468C119857082 @default.
• W2947372468 hasConceptScore W2947372468C138885662 @default.

• next