FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912684514> ?p ?o ?g. }

• W2912684514 endingPage "22" @default.
• W2912684514 startingPage "1" @default.
• W2912684514 abstract "Recent studies have shown that spatial relationships among objects are very important for visual recognition, since they can provide rich clues on object contexts within the images. In this article, we introduce a novel method to learn the Semantic Feature Map (SFM) with attention-based deep neural networks for image and video classification in an end-to-end manner, aiming to explicitly model the spatial object contexts within the images. In particular, we explicitly apply the designed gate units to the extracted object features for important objects selection and noise removal. These selected object features are then organized into the proposed SFM, which is a compact and discriminative representation with the spatial information among objects preserved. Finally, we employ either Fully Convolutional Networks (FCN) or Long-Short Term Memory (LSTM) as the classifiers on top of the SFM for content recognition. A novel multi-task learning framework with image classification loss, object localization loss, and grid labeling loss are also introduced to help better learn the model parameters. We conduct extensive evaluations and comparative studies to verify the effectiveness of the proposed approach on Pascal VOC 2007/2012 and MS-COCO benchmarks for image classification. In addition, the experimental results also show that the SFMs learned from the image domain can be successfully transferred to CCV and FCVID benchmarks for video classification." @default.
• W2912684514 created "2019-02-21" @default.
• W2912684514 creator A5013339942 @default.
• W2912684514 creator A5026167547 @default.
• W2912684514 creator A5031514811 @default.
• W2912684514 creator A5032517539 @default.
• W2912684514 creator A5047962986 @default.
• W2912684514 date "2019-01-31" @default.
• W2912684514 modified "2023-10-17" @default.
• W2912684514 title "Visual Content Recognition by Exploiting Semantic Feature Map with Attention and Multi-task Learning" @default.
• W2912684514 cites W1524680991 @default.
• W2912684514 cites W1536680647 @default.
• W2912684514 cites W1599220855 @default.
• W2912684514 cites W1777628566 @default.
• W2912684514 cites W1903029394 @default.
• W2912684514 cites W1965555842 @default.
• W2912684514 cites W1986482242 @default.
• W2912684514 cites W2010181071 @default.
• W2912684514 cites W2012592962 @default.
• W2912684514 cites W2035192458 @default.
• W2912684514 cites W2037227137 @default.
• W2912684514 cites W2063438554 @default.
• W2912684514 cites W2064675550 @default.
• W2912684514 cites W2066650804 @default.
• W2912684514 cites W2088049833 @default.
• W2912684514 cites W2093367888 @default.
• W2912684514 cites W2097117768 @default.
• W2912684514 cites W2102605133 @default.
• W2912684514 cites W2109255472 @default.
• W2912684514 cites W2110628941 @default.
• W2912684514 cites W2117539524 @default.
• W2912684514 cites W2142521298 @default.
• W2912684514 cites W2161381512 @default.
• W2912684514 cites W2161565164 @default.
• W2912684514 cites W2164507085 @default.
• W2912684514 cites W2191616647 @default.
• W2912684514 cites W2194775991 @default.
• W2912684514 cites W2257307118 @default.
• W2912684514 cites W2269165052 @default.
• W2912684514 cites W2473032611 @default.
• W2912684514 cites W2499974702 @default.
• W2912684514 cites W2521365688 @default.
• W2912684514 cites W2526479943 @default.
• W2912684514 cites W2527457059 @default.
• W2912684514 cites W2612703655 @default.
• W2912684514 cites W2765823242 @default.
• W2912684514 cites W2773003563 @default.
• W2912684514 cites W2963037989 @default.
• W2912684514 cites W2963173190 @default.
• W2912684514 cites W2963745697 @default.
• W2912684514 cites W2964227963 @default.
• W2912684514 cites W3124951096 @default.
• W2912684514 cites W2205968144 @default.
• W2912684514 doi "https://doi.org/10.1145/3231739" @default.
• W2912684514 hasPublicationYear "2019" @default.
• W2912684514 type Work @default.
• W2912684514 sameAs 2912684514 @default.
• W2912684514 citedByCount "3" @default.
• W2912684514 countsByYear W29126845142020 @default.
• W2912684514 countsByYear W29126845142021 @default.
• W2912684514 countsByYear W29126845142022 @default.
• W2912684514 crossrefType "journal-article" @default.
• W2912684514 hasAuthorship W2912684514A5013339942 @default.
• W2912684514 hasAuthorship W2912684514A5026167547 @default.
• W2912684514 hasAuthorship W2912684514A5031514811 @default.
• W2912684514 hasAuthorship W2912684514A5032517539 @default.
• W2912684514 hasAuthorship W2912684514A5047962986 @default.
• W2912684514 hasConcept C108583219 @default.
• W2912684514 hasConcept C138885662 @default.
• W2912684514 hasConcept C153180895 @default.
• W2912684514 hasConcept C154945302 @default.
• W2912684514 hasConcept C199360897 @default.
• W2912684514 hasConcept C2776151529 @default.
• W2912684514 hasConcept C2776401178 @default.
• W2912684514 hasConcept C2781238097 @default.
• W2912684514 hasConcept C31972630 @default.
• W2912684514 hasConcept C36464697 @default.
• W2912684514 hasConcept C41008148 @default.
• W2912684514 hasConcept C41895202 @default.
• W2912684514 hasConcept C52622490 @default.
• W2912684514 hasConcept C59404180 @default.
• W2912684514 hasConcept C64876066 @default.
• W2912684514 hasConcept C75608658 @default.
• W2912684514 hasConcept C81363708 @default.
• W2912684514 hasConcept C97931131 @default.
• W2912684514 hasConceptScore W2912684514C108583219 @default.
• W2912684514 hasConceptScore W2912684514C138885662 @default.
• W2912684514 hasConceptScore W2912684514C153180895 @default.
• W2912684514 hasConceptScore W2912684514C154945302 @default.
• W2912684514 hasConceptScore W2912684514C199360897 @default.
• W2912684514 hasConceptScore W2912684514C2776151529 @default.
• W2912684514 hasConceptScore W2912684514C2776401178 @default.
• W2912684514 hasConceptScore W2912684514C2781238097 @default.
• W2912684514 hasConceptScore W2912684514C31972630 @default.
• W2912684514 hasConceptScore W2912684514C36464697 @default.
• W2912684514 hasConceptScore W2912684514C41008148 @default.
• W2912684514 hasConceptScore W2912684514C41895202 @default.
• W2912684514 hasConceptScore W2912684514C52622490 @default.

• next