Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890124903> ?p ?o ?g. }
- W2890124903 abstract "Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks. However, due to data limitations, there has been much less work on video-based QA. In this paper, we present TVQA, a large-scale video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs from 21,793 clips, spanning over 460 hours of video. Questions are designed to be compositional in nature, requiring systems to jointly localize relevant moments within a clip, comprehend subtitle-based dialogue, and recognize relevant visual concepts. We provide analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVQA task. The dataset is publicly available at http://tvqa.cs.unc.edu." @default.
- W2890124903 created "2018-09-27" @default.
- W2890124903 creator A5001987532 @default.
- W2890124903 creator A5007285444 @default.
- W2890124903 creator A5008309880 @default.
- W2890124903 creator A5036418431 @default.
- W2890124903 date "2018-09-05" @default.
- W2890124903 modified "2023-09-24" @default.
- W2890124903 title "TVQA: Localized, Compositional Video Question Answering" @default.
- W2890124903 cites W1505802906 @default.
- W2890124903 cites W2108598243 @default.
- W2890124903 cites W2123395566 @default.
- W2890124903 cites W2125436846 @default.
- W2890124903 cites W2189070436 @default.
- W2890124903 cites W2194775991 @default.
- W2890124903 cites W2250539671 @default.
- W2890124903 cites W2427527485 @default.
- W2890124903 cites W2505639562 @default.
- W2890124903 cites W2561715562 @default.
- W2890124903 cites W2571175805 @default.
- W2890124903 cites W2726160912 @default.
- W2890124903 cites W2735159761 @default.
- W2890124903 cites W2737766105 @default.
- W2890124903 cites W2768661419 @default.
- W2890124903 cites W2784458614 @default.
- W2890124903 cites W2915649242 @default.
- W2890124903 cites W2949107813 @default.
- W2890124903 cites W2949218037 @default.
- W2890124903 cites W2949380904 @default.
- W2890124903 cites W2949615363 @default.
- W2890124903 cites W2950726992 @default.
- W2890124903 cites W2953106684 @default.
- W2890124903 cites W2962703144 @default.
- W2890124903 cites W2962749469 @default.
- W2890124903 cites W2962790689 @default.
- W2890124903 cites W2963017553 @default.
- W2890124903 cites W2963389687 @default.
- W2890124903 cites W2963564796 @default.
- W2890124903 cites W2963565375 @default.
- W2890124903 cites W2963735856 @default.
- W2890124903 cites W2963890755 @default.
- W2890124903 cites W2964089981 @default.
- W2890124903 cites W2964267515 @default.
- W2890124903 cites W2964322347 @default.
- W2890124903 cites W3098232790 @default.
- W2890124903 cites W627986001 @default.
- W2890124903 doi "https://doi.org/10.48550/arxiv.1809.01696" @default.
- W2890124903 hasPublicationYear "2018" @default.
- W2890124903 type Work @default.
- W2890124903 sameAs 2890124903 @default.
- W2890124903 citedByCount "17" @default.
- W2890124903 countsByYear W28901249032019 @default.
- W2890124903 countsByYear W28901249032020 @default.
- W2890124903 countsByYear W28901249032021 @default.
- W2890124903 crossrefType "posted-content" @default.
- W2890124903 hasAuthorship W2890124903A5001987532 @default.
- W2890124903 hasAuthorship W2890124903A5007285444 @default.
- W2890124903 hasAuthorship W2890124903A5008309880 @default.
- W2890124903 hasAuthorship W2890124903A5036418431 @default.
- W2890124903 hasBestOaLocation W28901249031 @default.
- W2890124903 hasConcept C111919701 @default.
- W2890124903 hasConcept C154945302 @default.
- W2890124903 hasConcept C162324750 @default.
- W2890124903 hasConcept C187736073 @default.
- W2890124903 hasConcept C204321447 @default.
- W2890124903 hasConcept C23123220 @default.
- W2890124903 hasConcept C2778739407 @default.
- W2890124903 hasConcept C2780364048 @default.
- W2890124903 hasConcept C2780451532 @default.
- W2890124903 hasConcept C2983174267 @default.
- W2890124903 hasConcept C2984842247 @default.
- W2890124903 hasConcept C41008148 @default.
- W2890124903 hasConcept C44291984 @default.
- W2890124903 hasConcept C50644808 @default.
- W2890124903 hasConceptScore W2890124903C111919701 @default.
- W2890124903 hasConceptScore W2890124903C154945302 @default.
- W2890124903 hasConceptScore W2890124903C162324750 @default.
- W2890124903 hasConceptScore W2890124903C187736073 @default.
- W2890124903 hasConceptScore W2890124903C204321447 @default.
- W2890124903 hasConceptScore W2890124903C23123220 @default.
- W2890124903 hasConceptScore W2890124903C2778739407 @default.
- W2890124903 hasConceptScore W2890124903C2780364048 @default.
- W2890124903 hasConceptScore W2890124903C2780451532 @default.
- W2890124903 hasConceptScore W2890124903C2983174267 @default.
- W2890124903 hasConceptScore W2890124903C2984842247 @default.
- W2890124903 hasConceptScore W2890124903C41008148 @default.
- W2890124903 hasConceptScore W2890124903C44291984 @default.
- W2890124903 hasConceptScore W2890124903C50644808 @default.
- W2890124903 hasLocation W28901249031 @default.
- W2890124903 hasOpenAccess W2890124903 @default.
- W2890124903 hasPrimaryLocation W28901249031 @default.
- W2890124903 hasRelatedWork W1500337239 @default.
- W2890124903 hasRelatedWork W1507754474 @default.
- W2890124903 hasRelatedWork W1511492033 @default.
- W2890124903 hasRelatedWork W1864692919 @default.
- W2890124903 hasRelatedWork W2348101466 @default.
- W2890124903 hasRelatedWork W2890124903 @default.
- W2890124903 hasRelatedWork W2918156780 @default.
- W2890124903 hasRelatedWork W2963541336 @default.
- W2890124903 hasRelatedWork W9662544 @default.