Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306353243> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4306353243 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 (such as: under, in front of, and 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." @default.
- W4306353243 created "2022-10-16" @default.
- W4306353243 creator A5026154387 @default.
- W4306353243 creator A5073413742 @default.
- W4306353243 creator A5076539912 @default.
- W4306353243 date "2022-04-30" @default.
- W4306353243 modified "2023-10-16" @default.
- W4306353243 title "Visual Spatial Reasoning" @default.
- W4306353243 doi "https://doi.org/10.48550/arxiv.2205.00363" @default.
- W4306353243 hasPublicationYear "2022" @default.
- W4306353243 type Work @default.
- W4306353243 citedByCount "0" @default.
- W4306353243 crossrefType "posted-content" @default.
- W4306353243 hasAuthorship W4306353243A5026154387 @default.
- W4306353243 hasAuthorship W4306353243A5073413742 @default.
- W4306353243 hasAuthorship W4306353243A5076539912 @default.
- W4306353243 hasBestOaLocation W43063532431 @default.
- W4306353243 hasConcept C124101348 @default.
- W4306353243 hasConcept C136197465 @default.
- W4306353243 hasConcept C154945302 @default.
- W4306353243 hasConcept C155911833 @default.
- W4306353243 hasConcept C166957645 @default.
- W4306353243 hasConcept C195324797 @default.
- W4306353243 hasConcept C204321447 @default.
- W4306353243 hasConcept C205649164 @default.
- W4306353243 hasConcept C25343380 @default.
- W4306353243 hasConcept C27511587 @default.
- W4306353243 hasConcept C2776321320 @default.
- W4306353243 hasConcept C2776608160 @default.
- W4306353243 hasConcept C2777508537 @default.
- W4306353243 hasConcept C41008148 @default.
- W4306353243 hasConceptScore W4306353243C124101348 @default.
- W4306353243 hasConceptScore W4306353243C136197465 @default.
- W4306353243 hasConceptScore W4306353243C154945302 @default.
- W4306353243 hasConceptScore W4306353243C155911833 @default.
- W4306353243 hasConceptScore W4306353243C166957645 @default.
- W4306353243 hasConceptScore W4306353243C195324797 @default.
- W4306353243 hasConceptScore W4306353243C204321447 @default.
- W4306353243 hasConceptScore W4306353243C205649164 @default.
- W4306353243 hasConceptScore W4306353243C25343380 @default.
- W4306353243 hasConceptScore W4306353243C27511587 @default.
- W4306353243 hasConceptScore W4306353243C2776321320 @default.
- W4306353243 hasConceptScore W4306353243C2776608160 @default.
- W4306353243 hasConceptScore W4306353243C2777508537 @default.
- W4306353243 hasConceptScore W4306353243C41008148 @default.
- W4306353243 hasLocation W43063532431 @default.
- W4306353243 hasOpenAccess W4306353243 @default.
- W4306353243 hasPrimaryLocation W43063532431 @default.
- W4306353243 hasRelatedWork W23606365 @default.
- W4306353243 hasRelatedWork W2360900871 @default.
- W4306353243 hasRelatedWork W2367213291 @default.
- W4306353243 hasRelatedWork W2368307623 @default.
- W4306353243 hasRelatedWork W2382163390 @default.
- W4306353243 hasRelatedWork W2389250197 @default.
- W4306353243 hasRelatedWork W3107474891 @default.
- W4306353243 hasRelatedWork W38394648 @default.
- W4306353243 hasRelatedWork W4306353243 @default.
- W4306353243 hasRelatedWork W1967100394 @default.
- W4306353243 isParatext "false" @default.
- W4306353243 isRetracted "false" @default.
- W4306353243 workType "article" @default.