Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381802186> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4381802186 endingPage "651" @default.
- W4381802186 startingPage "635" @default.
- W4381802186 abstract "Abstract Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational information. In this paper, we present Visual Spatial Reasoning (VSR), a dataset containing more than 10k natural text-image pairs with 66 types of spatial relations in English (e.g., under, in front of, facing). While using a seemingly simple annotation format, we show how the dataset includes challenging linguistic phenomena, such as varying reference frames. We demonstrate a large gap between human and model performance: The human ceiling is above 95%, while state-of-the-art models only achieve around 70%. We observe that VLMs’ by-relation performances have little correlation with the number of training examples and the tested models are in general incapable of recognising relations concerning the orientations of objects.1" @default.
- W4381802186 created "2023-06-24" @default.
- W4381802186 creator A5026154387 @default.
- W4381802186 creator A5073413742 @default.
- W4381802186 creator A5076539912 @default.
- W4381802186 date "2023-01-01" @default.
- W4381802186 modified "2023-10-16" @default.
- W4381802186 title "Visual Spatial Reasoning" @default.
- W4381802186 cites W1519642452 @default.
- W4381802186 cites W1801951652 @default.
- W4381802186 cites W1861492603 @default.
- W4381802186 cites W1933349210 @default.
- W4381802186 cites W2128092632 @default.
- W4381802186 cites W2164777277 @default.
- W4381802186 cites W2277195237 @default.
- W4381802186 cites W2462848072 @default.
- W4381802186 cites W2560730294 @default.
- W4381802186 cites W2561715562 @default.
- W4381802186 cites W2741631785 @default.
- W4381802186 cites W2803125506 @default.
- W4381802186 cites W2891914492 @default.
- W4381802186 cites W2907143950 @default.
- W4381802186 cites W2963115613 @default.
- W4381802186 cites W2963393863 @default.
- W4381802186 cites W2963518342 @default.
- W4381802186 cites W2963530300 @default.
- W4381802186 cites W2964166221 @default.
- W4381802186 cites W2970231061 @default.
- W4381802186 cites W3034381157 @default.
- W4381802186 cites W3034636873 @default.
- W4381802186 cites W3153839026 @default.
- W4381802186 cites W3177487519 @default.
- W4381802186 cites W3192859517 @default.
- W4381802186 cites W3201264086 @default.
- W4381802186 cites W3202415077 @default.
- W4381802186 cites W3213454282 @default.
- W4381802186 cites W4224598161 @default.
- W4381802186 cites W4226095990 @default.
- W4381802186 cites W4281633937 @default.
- W4381802186 cites W4285192809 @default.
- W4381802186 cites W4287854770 @default.
- W4381802186 doi "https://doi.org/10.1162/tacl_a_00566" @default.
- W4381802186 hasPublicationYear "2023" @default.
- W4381802186 type Work @default.
- W4381802186 citedByCount "0" @default.
- W4381802186 crossrefType "journal-article" @default.
- W4381802186 hasAuthorship W4381802186A5026154387 @default.
- W4381802186 hasAuthorship W4381802186A5073413742 @default.
- W4381802186 hasAuthorship W4381802186A5076539912 @default.
- W4381802186 hasBestOaLocation W43818021861 @default.
- W4381802186 hasConcept C124101348 @default.
- W4381802186 hasConcept C136197465 @default.
- W4381802186 hasConcept C154945302 @default.
- W4381802186 hasConcept C155911833 @default.
- W4381802186 hasConcept C166957645 @default.
- W4381802186 hasConcept C195324797 @default.
- W4381802186 hasConcept C204321447 @default.
- W4381802186 hasConcept C25343380 @default.
- W4381802186 hasConcept C27511587 @default.
- W4381802186 hasConcept C2776321320 @default.
- W4381802186 hasConcept C2776608160 @default.
- W4381802186 hasConcept C2777508537 @default.
- W4381802186 hasConcept C41008148 @default.
- W4381802186 hasConcept C95457728 @default.
- W4381802186 hasConceptScore W4381802186C124101348 @default.
- W4381802186 hasConceptScore W4381802186C136197465 @default.
- W4381802186 hasConceptScore W4381802186C154945302 @default.
- W4381802186 hasConceptScore W4381802186C155911833 @default.
- W4381802186 hasConceptScore W4381802186C166957645 @default.
- W4381802186 hasConceptScore W4381802186C195324797 @default.
- W4381802186 hasConceptScore W4381802186C204321447 @default.
- W4381802186 hasConceptScore W4381802186C25343380 @default.
- W4381802186 hasConceptScore W4381802186C27511587 @default.
- W4381802186 hasConceptScore W4381802186C2776321320 @default.
- W4381802186 hasConceptScore W4381802186C2776608160 @default.
- W4381802186 hasConceptScore W4381802186C2777508537 @default.
- W4381802186 hasConceptScore W4381802186C41008148 @default.
- W4381802186 hasConceptScore W4381802186C95457728 @default.
- W4381802186 hasLocation W43818021861 @default.
- W4381802186 hasOpenAccess W4381802186 @default.
- W4381802186 hasPrimaryLocation W43818021861 @default.
- W4381802186 hasRelatedWork W1976895794 @default.
- W4381802186 hasRelatedWork W23606365 @default.
- W4381802186 hasRelatedWork W2367213291 @default.
- W4381802186 hasRelatedWork W2389250197 @default.
- W4381802186 hasRelatedWork W2519891957 @default.
- W4381802186 hasRelatedWork W38394648 @default.
- W4381802186 hasRelatedWork W4306353243 @default.
- W4381802186 hasRelatedWork W4381802186 @default.
- W4381802186 hasRelatedWork W1967100394 @default.
- W4381802186 hasRelatedWork W2584532118 @default.
- W4381802186 hasVolume "11" @default.
- W4381802186 isParatext "false" @default.
- W4381802186 isRetracted "false" @default.
- W4381802186 workType "article" @default.