FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969897437> ?p ?o ?g. }

• W2969897437 endingPage "1041" @default.
• W2969897437 startingPage "1032" @default.
• W2969897437 abstract "Vision and language understanding is one of the most fundamental and challenging problems in Multimedia Intelligence. Simultaneously understanding video actions with a related natural language question, and further produces accurate answer is even more challenging since it requires joint modeling information across modality. In the past few years, some studies begin to attack this problem by utilizing attention enhanced deep neural networks. However, simple attention mechanisms such as unidirectional attention fail to yield a better mapping between different modalities. Moreover, none of these Video QA models explore high-level semantics in augmented video-frame level. In this paper, we augmented each frame representation with its context information by a novel feature extractor that combines the advantages of Resnet and a variant of C3D. In addition, we proposed a novel alternating attention network which can alternately attend frame regions, video frames and words in the question in multi-turns. This yields better joint representations of video and question, further help the deep model to discover the deeper relationship between two modalities. Our method outperforms the state-of-the-art Video QA models on two existing video question answering datasets. Further ablation studies proved that our feature extractor and the alternating attention mechanism can improve the performance jointly." @default.
• W2969897437 created "2019-08-29" @default.
• W2969897437 creator A5008666077 @default.
• W2969897437 creator A5012288572 @default.
• W2969897437 creator A5014111141 @default.
• W2969897437 creator A5063062444 @default.
• W2969897437 creator A5082131901 @default.
• W2969897437 creator A5085955762 @default.
• W2969897437 date "2020-04-01" @default.
• W2969897437 modified "2023-10-09" @default.
• W2969897437 title "Frame Augmented Alternating Attention Network for Video Question Answering" @default.
• W2969897437 cites W1518233497 @default.
• W2969897437 cites W1522734439 @default.
• W2969897437 cites W1586939924 @default.
• W2969897437 cites W1933349210 @default.
• W2969897437 cites W1965963232 @default.
• W2969897437 cites W2013822448 @default.
• W2969897437 cites W2026012689 @default.
• W2969897437 cites W2112193096 @default.
• W2969897437 cites W2166348853 @default.
• W2969897437 cites W2194775991 @default.
• W2969897437 cites W2250539671 @default.
• W2969897437 cites W2425121537 @default.
• W2969897437 cites W2520610372 @default.
• W2969897437 cites W2527089194 @default.
• W2969897437 cites W2549699157 @default.
• W2969897437 cites W2573426660 @default.
• W2969897437 cites W2590526842 @default.
• W2969897437 cites W2593722617 @default.
• W2969897437 cites W2606982687 @default.
• W2969897437 cites W2737435850 @default.
• W2969897437 cites W2747623286 @default.
• W2969897437 cites W2765716052 @default.
• W2969897437 cites W2766690867 @default.
• W2969897437 cites W2798786641 @default.
• W2969897437 cites W2963150162 @default.
• W2969897437 cites W2963191264 @default.
• W2969897437 cites W2963954913 @default.
• W2969897437 cites W2964022527 @default.
• W2969897437 cites W2964220823 @default.
• W2969897437 cites W3124951096 @default.
• W2969897437 doi "https://doi.org/10.1109/tmm.2019.2935678" @default.
• W2969897437 hasPublicationYear "2020" @default.
• W2969897437 type Work @default.
• W2969897437 sameAs 2969897437 @default.
• W2969897437 citedByCount "35" @default.
• W2969897437 countsByYear W29698974372020 @default.
• W2969897437 countsByYear W29698974372021 @default.
• W2969897437 countsByYear W29698974372022 @default.
• W2969897437 countsByYear W29698974372023 @default.
• W2969897437 crossrefType "journal-article" @default.
• W2969897437 hasAuthorship W2969897437A5008666077 @default.
• W2969897437 hasAuthorship W2969897437A5012288572 @default.
• W2969897437 hasAuthorship W2969897437A5014111141 @default.
• W2969897437 hasAuthorship W2969897437A5063062444 @default.
• W2969897437 hasAuthorship W2969897437A5082131901 @default.
• W2969897437 hasAuthorship W2969897437A5085955762 @default.
• W2969897437 hasConcept C126042441 @default.
• W2969897437 hasConcept C138885662 @default.
• W2969897437 hasConcept C144024400 @default.
• W2969897437 hasConcept C151730666 @default.
• W2969897437 hasConcept C154945302 @default.
• W2969897437 hasConcept C17744445 @default.
• W2969897437 hasConcept C184337299 @default.
• W2969897437 hasConcept C199360897 @default.
• W2969897437 hasConcept C199539241 @default.
• W2969897437 hasConcept C2776359362 @default.
• W2969897437 hasConcept C2776401178 @default.
• W2969897437 hasConcept C2779343474 @default.
• W2969897437 hasConcept C2779903281 @default.
• W2969897437 hasConcept C2780226545 @default.
• W2969897437 hasConcept C36289849 @default.
• W2969897437 hasConcept C41008148 @default.
• W2969897437 hasConcept C41895202 @default.
• W2969897437 hasConcept C44291984 @default.
• W2969897437 hasConcept C76155785 @default.
• W2969897437 hasConcept C86803240 @default.
• W2969897437 hasConcept C94625758 @default.
• W2969897437 hasConceptScore W2969897437C126042441 @default.
• W2969897437 hasConceptScore W2969897437C138885662 @default.
• W2969897437 hasConceptScore W2969897437C144024400 @default.
• W2969897437 hasConceptScore W2969897437C151730666 @default.
• W2969897437 hasConceptScore W2969897437C154945302 @default.
• W2969897437 hasConceptScore W2969897437C17744445 @default.
• W2969897437 hasConceptScore W2969897437C184337299 @default.
• W2969897437 hasConceptScore W2969897437C199360897 @default.
• W2969897437 hasConceptScore W2969897437C199539241 @default.
• W2969897437 hasConceptScore W2969897437C2776359362 @default.
• W2969897437 hasConceptScore W2969897437C2776401178 @default.
• W2969897437 hasConceptScore W2969897437C2779343474 @default.
• W2969897437 hasConceptScore W2969897437C2779903281 @default.
• W2969897437 hasConceptScore W2969897437C2780226545 @default.
• W2969897437 hasConceptScore W2969897437C36289849 @default.
• W2969897437 hasConceptScore W2969897437C41008148 @default.
• W2969897437 hasConceptScore W2969897437C41895202 @default.
• W2969897437 hasConceptScore W2969897437C44291984 @default.
• W2969897437 hasConceptScore W2969897437C76155785 @default.
• W2969897437 hasConceptScore W2969897437C86803240 @default.

• next