Matches in SemOpenAlex for { <https://semopenalex.org/work/W3012155113> ?p ?o ?g. }
- W3012155113 abstract "Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent's actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations, and transformations of the objects in the scene, are reflected in conventional video captioning. Unlike images, actions in videos are also inherently linked to social aspects such as intentions (why the action is taking place), effects (what changes due to the action), and attributes that describe the agent. Thus for video understanding, such as when captioning videos or when answering questions about videos, one must have an understanding of these commonsense aspects. We present the first work on generating commonsense captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. We present a new dataset Video-to-Commonsense (V2C) that contains $sim9k$ videos of human agents performing various actions, annotated with 3 types of commonsense descriptions. Additionally we explore the use of open-ended video-based commonsense question answering (V2C-QA) as a way to enrich our captions. Both the generation task and the QA task can be used to enrich video captions." @default.
- W3012155113 created "2020-03-23" @default.
- W3012155113 creator A5002278578 @default.
- W3012155113 creator A5017986865 @default.
- W3012155113 creator A5035343276 @default.
- W3012155113 creator A5065602294 @default.
- W3012155113 creator A5083735830 @default.
- W3012155113 date "2020-03-11" @default.
- W3012155113 modified "2023-09-24" @default.
- W3012155113 title "Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning" @default.
- W3012155113 cites W1525961042 @default.
- W3012155113 cites W1858383477 @default.
- W3012155113 cites W1933349210 @default.
- W3012155113 cites W2101105183 @default.
- W3012155113 cites W2108598243 @default.
- W3012155113 cites W2123301721 @default.
- W3012155113 cites W2139117248 @default.
- W3012155113 cites W2139501017 @default.
- W3012155113 cites W2141080726 @default.
- W3012155113 cites W2154652894 @default.
- W3012155113 cites W2194775991 @default.
- W3012155113 cites W2196779496 @default.
- W3012155113 cites W2202226326 @default.
- W3012155113 cites W2251329024 @default.
- W3012155113 cites W2251353663 @default.
- W3012155113 cites W2402268235 @default.
- W3012155113 cites W2423576022 @default.
- W3012155113 cites W2425121537 @default.
- W3012155113 cites W2463873473 @default.
- W3012155113 cites W2549599535 @default.
- W3012155113 cites W2558834163 @default.
- W3012155113 cites W2561715562 @default.
- W3012155113 cites W2735159761 @default.
- W3012155113 cites W2739107216 @default.
- W3012155113 cites W2765716052 @default.
- W3012155113 cites W2781474777 @default.
- W3012155113 cites W2795840542 @default.
- W3012155113 cites W2798746229 @default.
- W3012155113 cites W2804447833 @default.
- W3012155113 cites W2885138528 @default.
- W3012155113 cites W2898867267 @default.
- W3012155113 cites W2946989343 @default.
- W3012155113 cites W2949433733 @default.
- W3012155113 cites W2950104027 @default.
- W3012155113 cites W2950339735 @default.
- W3012155113 cites W2950761309 @default.
- W3012155113 cites W2963115613 @default.
- W3012155113 cites W2963341956 @default.
- W3012155113 cites W2963352593 @default.
- W3012155113 cites W2963541336 @default.
- W3012155113 cites W2963890755 @default.
- W3012155113 cites W2963916161 @default.
- W3012155113 cites W2963983586 @default.
- W3012155113 cites W2963995027 @default.
- W3012155113 cites W2965373594 @default.
- W3012155113 cites W2969746393 @default.
- W3012155113 cites W2970062726 @default.
- W3012155113 cites W2970231061 @default.
- W3012155113 cites W2981851019 @default.
- W3012155113 cites W2995643077 @default.
- W3012155113 cites W2998617917 @default.
- W3012155113 cites W3098232790 @default.
- W3012155113 cites W3106768499 @default.
- W3012155113 cites W3110388292 @default.
- W3012155113 cites W46519926 @default.
- W3012155113 doi "https://doi.org/10.48550/arxiv.2003.05162" @default.
- W3012155113 hasPublicationYear "2020" @default.
- W3012155113 type Work @default.
- W3012155113 sameAs 3012155113 @default.
- W3012155113 citedByCount "3" @default.
- W3012155113 countsByYear W30121551132020 @default.
- W3012155113 crossrefType "posted-content" @default.
- W3012155113 hasAuthorship W3012155113A5002278578 @default.
- W3012155113 hasAuthorship W3012155113A5017986865 @default.
- W3012155113 hasAuthorship W3012155113A5035343276 @default.
- W3012155113 hasAuthorship W3012155113A5065602294 @default.
- W3012155113 hasAuthorship W3012155113A5083735830 @default.
- W3012155113 hasBestOaLocation W30121551131 @default.
- W3012155113 hasConcept C107457646 @default.
- W3012155113 hasConcept C115961682 @default.
- W3012155113 hasConcept C120567893 @default.
- W3012155113 hasConcept C121332964 @default.
- W3012155113 hasConcept C154945302 @default.
- W3012155113 hasConcept C157657479 @default.
- W3012155113 hasConcept C162324750 @default.
- W3012155113 hasConcept C187736073 @default.
- W3012155113 hasConcept C193221554 @default.
- W3012155113 hasConcept C204321447 @default.
- W3012155113 hasConcept C2780451532 @default.
- W3012155113 hasConcept C2780791683 @default.
- W3012155113 hasConcept C30542707 @default.
- W3012155113 hasConcept C41008148 @default.
- W3012155113 hasConcept C44291984 @default.
- W3012155113 hasConcept C62520636 @default.
- W3012155113 hasConceptScore W3012155113C107457646 @default.
- W3012155113 hasConceptScore W3012155113C115961682 @default.
- W3012155113 hasConceptScore W3012155113C120567893 @default.
- W3012155113 hasConceptScore W3012155113C121332964 @default.
- W3012155113 hasConceptScore W3012155113C154945302 @default.
- W3012155113 hasConceptScore W3012155113C157657479 @default.