FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093817292> ?p ?o ?g. }

• W3093817292 abstract "Video QA challenges modelers in multiple fronts. Modeling video necessitates building not only spatio-temporal models for the dynamic visual channel but also multimodal structures for associated information channels such as subtitles or audio. Video QA adds at least two more layers of complexity - selecting relevant content for each channel in the context of the linguistic query, and composing spatio-temporal concepts and relations in response to the query. To address these requirements, we start with two insights: (a) content selection and relation construction can be jointly encapsulated into a conditional computational structure, and (b) video-length structures can be composed hierarchically. For (a) this paper introduces a general-reusable neural unit dubbed Conditional Relation Network (CRN) taking as input a set of tensorial objects and translating into a new set of objects that encode relations of the inputs. The generic design of CRN helps ease the common complex model building process of Video QA by simple block stacking with flexibility in accommodating input modalities and conditioning features across both different domains. As a result, we realize insight (b) by introducing Hierarchical Conditional Relation Networks (HCRN) for Video QA. The HCRN primarily aims at exploiting intrinsic properties of the visual content of a video and its accompanying channels in terms of compositionality, hierarchy, and near and far-term relation. HCRN is then applied for Video QA in two forms, short-form where answers are reasoned solely from the visual content, and long-form where associated information, such as subtitles, presented. Our rigorous evaluations show consistent improvements over SOTAs on well-studied benchmarks including large-scale real-world datasets such as TGIF-QA and TVQA, demonstrating the strong capabilities of our CRN unit and the HCRN for complex domains such as Video QA." @default.
• W3093817292 created "2020-10-29" @default.
• W3093817292 creator A5029157904 @default.
• W3093817292 creator A5045540854 @default.
• W3093817292 creator A5079045166 @default.
• W3093817292 creator A5085471517 @default.
• W3093817292 date "2020-10-18" @default.
• W3093817292 modified "2023-10-16" @default.
• W3093817292 title "Hierarchical Conditional Relation Networks for Multimodal Video Question Answering" @default.
• W3093817292 cites W1996423919 @default.
• W3093817292 cites W2049389369 @default.
• W3093817292 cites W2064675550 @default.
• W3093817292 cites W2097117768 @default.
• W3093817292 cites W2144125753 @default.
• W3093817292 cites W2194775991 @default.
• W3093817292 cites W2250539671 @default.
• W3093817292 cites W2425121537 @default.
• W3093817292 cites W2549139847 @default.
• W3093817292 cites W2735159761 @default.
• W3093817292 cites W2741903908 @default.
• W3093817292 cites W2761659801 @default.
• W3093817292 cites W2765716052 @default.
• W3093817292 cites W2770804203 @default.
• W3093817292 cites W2795916123 @default.
• W3093817292 cites W2798786641 @default.
• W3093817292 cites W2808124938 @default.
• W3093817292 cites W2885775891 @default.
• W3093817292 cites W2890598214 @default.
• W3093817292 cites W2890904455 @default.
• W3093817292 cites W2897857500 @default.
• W3093817292 cites W2904452845 @default.
• W3093817292 cites W2951024719 @default.
• W3093817292 cites W2951815760 @default.
• W3093817292 cites W2952620298 @default.
• W3093817292 cites W2954199749 @default.
• W3093817292 cites W2955874753 @default.
• W3093817292 cites W2962910007 @default.
• W3093817292 cites W2962934715 @default.
• W3093817292 cites W2962938145 @default.
• W3093817292 cites W2962949233 @default.
• W3093817292 cites W2963150162 @default.
• W3093817292 cites W2963155035 @default.
• W3093817292 cites W2963285578 @default.
• W3093817292 cites W2963341956 @default.
• W3093817292 cites W2963521239 @default.
• W3093817292 cites W2963541336 @default.
• W3093817292 cites W2963781647 @default.
• W3093817292 cites W2963843052 @default.
• W3093817292 cites W2963921132 @default.
• W3093817292 cites W2965527197 @default.
• W3093817292 cites W2969127500 @default.
• W3093817292 cites W2981582341 @default.
• W3093817292 cites W2981985547 @default.
• W3093817292 cites W2982139784 @default.
• W3093817292 cites W3008341877 @default.
• W3093817292 cites W3010593057 @default.
• W3093817292 cites W3023700693 @default.
• W3093817292 cites W3023993913 @default.
• W3093817292 cites W3089358914 @default.
• W3093817292 cites W3099904761 @default.
• W3093817292 hasPublicationYear "2020" @default.
• W3093817292 type Work @default.
• W3093817292 sameAs 3093817292 @default.
• W3093817292 citedByCount "0" @default.
• W3093817292 crossrefType "posted-content" @default.
• W3093817292 hasAuthorship W3093817292A5029157904 @default.
• W3093817292 hasAuthorship W3093817292A5045540854 @default.
• W3093817292 hasAuthorship W3093817292A5079045166 @default.
• W3093817292 hasAuthorship W3093817292A5085471517 @default.
• W3093817292 hasConcept C105795698 @default.
• W3093817292 hasConcept C111919701 @default.
• W3093817292 hasConcept C121375916 @default.
• W3093817292 hasConcept C124101348 @default.
• W3093817292 hasConcept C127162648 @default.
• W3093817292 hasConcept C151730666 @default.
• W3093817292 hasConcept C154945302 @default.
• W3093817292 hasConcept C162324750 @default.
• W3093817292 hasConcept C177264268 @default.
• W3093817292 hasConcept C199360897 @default.
• W3093817292 hasConcept C23123220 @default.
• W3093817292 hasConcept C25343380 @default.
• W3093817292 hasConcept C2779343474 @default.
• W3093817292 hasConcept C2780598303 @default.
• W3093817292 hasConcept C31170391 @default.
• W3093817292 hasConcept C31258907 @default.
• W3093817292 hasConcept C33923547 @default.
• W3093817292 hasConcept C34447519 @default.
• W3093817292 hasConcept C41008148 @default.
• W3093817292 hasConcept C86803240 @default.
• W3093817292 hasConcept C98045186 @default.
• W3093817292 hasConceptScore W3093817292C105795698 @default.
• W3093817292 hasConceptScore W3093817292C111919701 @default.
• W3093817292 hasConceptScore W3093817292C121375916 @default.
• W3093817292 hasConceptScore W3093817292C124101348 @default.
• W3093817292 hasConceptScore W3093817292C127162648 @default.
• W3093817292 hasConceptScore W3093817292C151730666 @default.
• W3093817292 hasConceptScore W3093817292C154945302 @default.
• W3093817292 hasConceptScore W3093817292C162324750 @default.
• W3093817292 hasConceptScore W3093817292C177264268 @default.
• W3093817292 hasConceptScore W3093817292C199360897 @default.

• next