Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094619608> ?p ?o ?g. }
- W3094619608 abstract "Video-grounded dialogues are very challenging due to (i) the complexity of videos which contain both spatial and temporal variations, and (ii) the complexity of user utterances which query different segments and/or different objects in videos over multiple dialogue turns. However, existing approaches to video-grounded dialogues often focus on superficial temporal-level visual cues, but neglect more fine-grained spatial signals from videos. To address this drawback, we propose Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in videos based on textual cues. Specifically, our approach not only exploits both spatial and temporal-level information, but also learns dynamic information diffusion between the two feature spaces through spatial-to-temporal and temporal-to-spatial reasoning. The bidirectional strategy aims to tackle the evolving semantics of user queries in the dialogue setting. The retrieved visual cues are used as contextual information to construct relevant responses to the users. Our empirical results and comprehensive qualitative analysis show that BiST achieves competitive performance and generates reasonable responses on a large-scale AVSD benchmark. We also adapt our BiST models to the Video QA setting, and substantially outperform prior approaches on the TGIF-QA benchmark." @default.
- W3094619608 created "2020-10-29" @default.
- W3094619608 creator A5014190404 @default.
- W3094619608 creator A5018199981 @default.
- W3094619608 creator A5074834854 @default.
- W3094619608 creator A5078515449 @default.
- W3094619608 date "2020-10-20" @default.
- W3094619608 modified "2023-09-23" @default.
- W3094619608 title "BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues" @default.
- W3094619608 cites W1514535095 @default.
- W3094619608 cites W1522734439 @default.
- W3094619608 cites W1533861849 @default.
- W3094619608 cites W1575833922 @default.
- W3094619608 cites W1933349210 @default.
- W3094619608 cites W1947481528 @default.
- W3094619608 cites W1956340063 @default.
- W3094619608 cites W2101105183 @default.
- W3094619608 cites W2123301721 @default.
- W3094619608 cites W2131774270 @default.
- W3094619608 cites W2154652894 @default.
- W3094619608 cites W2156303437 @default.
- W3094619608 cites W2183341477 @default.
- W3094619608 cites W2194775991 @default.
- W3094619608 cites W2337252826 @default.
- W3094619608 cites W2342662179 @default.
- W3094619608 cites W2427527485 @default.
- W3094619608 cites W2507756961 @default.
- W3094619608 cites W2526449353 @default.
- W3094619608 cites W2549139847 @default.
- W3094619608 cites W2560730294 @default.
- W3094619608 cites W2565656701 @default.
- W3094619608 cites W2810643877 @default.
- W3094619608 cites W2810840719 @default.
- W3094619608 cites W2891732163 @default.
- W3094619608 cites W2904291752 @default.
- W3094619608 cites W2904452845 @default.
- W3094619608 cites W2911400095 @default.
- W3094619608 cites W2920113034 @default.
- W3094619608 cites W2937305817 @default.
- W3094619608 cites W2948048211 @default.
- W3094619608 cites W2950178297 @default.
- W3094619608 cites W2950761309 @default.
- W3094619608 cites W2951390634 @default.
- W3094619608 cites W2956387449 @default.
- W3094619608 cites W2962934715 @default.
- W3094619608 cites W2962949233 @default.
- W3094619608 cites W2963383024 @default.
- W3094619608 cites W2963403868 @default.
- W3094619608 cites W2963524571 @default.
- W3094619608 cites W2963529931 @default.
- W3094619608 cites W2963541336 @default.
- W3094619608 cites W2963576560 @default.
- W3094619608 cites W2963823251 @default.
- W3094619608 cites W2963890755 @default.
- W3094619608 cites W2964121744 @default.
- W3094619608 cites W2964218959 @default.
- W3094619608 cites W2968553732 @default.
- W3094619608 cites W2972745026 @default.
- W3094619608 cites W2997805943 @default.
- W3094619608 cites W2998166190 @default.
- W3094619608 cites W3034730770 @default.
- W3094619608 doi "https://doi.org/10.48550/arxiv.2010.10095" @default.
- W3094619608 hasPublicationYear "2020" @default.
- W3094619608 type Work @default.
- W3094619608 sameAs 3094619608 @default.
- W3094619608 citedByCount "0" @default.
- W3094619608 crossrefType "posted-content" @default.
- W3094619608 hasAuthorship W3094619608A5014190404 @default.
- W3094619608 hasAuthorship W3094619608A5018199981 @default.
- W3094619608 hasAuthorship W3094619608A5074834854 @default.
- W3094619608 hasAuthorship W3094619608A5078515449 @default.
- W3094619608 hasBestOaLocation W30946196081 @default.
- W3094619608 hasConcept C107457646 @default.
- W3094619608 hasConcept C119857082 @default.
- W3094619608 hasConcept C120665830 @default.
- W3094619608 hasConcept C121332964 @default.
- W3094619608 hasConcept C13280743 @default.
- W3094619608 hasConcept C138885662 @default.
- W3094619608 hasConcept C154945302 @default.
- W3094619608 hasConcept C165696696 @default.
- W3094619608 hasConcept C184337299 @default.
- W3094619608 hasConcept C185798385 @default.
- W3094619608 hasConcept C192209626 @default.
- W3094619608 hasConcept C199360897 @default.
- W3094619608 hasConcept C205649164 @default.
- W3094619608 hasConcept C2776401178 @default.
- W3094619608 hasConcept C2780801425 @default.
- W3094619608 hasConcept C38652104 @default.
- W3094619608 hasConcept C41008148 @default.
- W3094619608 hasConcept C41895202 @default.
- W3094619608 hasConceptScore W3094619608C107457646 @default.
- W3094619608 hasConceptScore W3094619608C119857082 @default.
- W3094619608 hasConceptScore W3094619608C120665830 @default.
- W3094619608 hasConceptScore W3094619608C121332964 @default.
- W3094619608 hasConceptScore W3094619608C13280743 @default.
- W3094619608 hasConceptScore W3094619608C138885662 @default.
- W3094619608 hasConceptScore W3094619608C154945302 @default.
- W3094619608 hasConceptScore W3094619608C165696696 @default.
- W3094619608 hasConceptScore W3094619608C184337299 @default.
- W3094619608 hasConceptScore W3094619608C185798385 @default.