Matches in SemOpenAlex for { <https://semopenalex.org/work/W3039731725> ?p ?o ?g. }
- W3039731725 abstract "Explainability is one of the key elements for building trust in AI systems. Among numerous attempts to make AI explainable, quantifying the effect of explanations remains a challenge in conducting human-AI collaborative tasks. Aside from the ability to predict the overall behavior of AI, in many applications, users need to understand an AI agent's competency in different aspects of the task domain. In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA). We quantify users' understanding of competency, based on the correlation between the actual system performance and user rankings. We introduce an explainable VQA system that uses spatial and object features and is powered by the BERT language model. Each group of users sees only one kind of explanation to rank the competencies of the VQA model. The proposed model is evaluated through between-subject experiments to probe explanations' impact on the user's perception of competency. The comparison between two VQA models shows BERT based explanations and the use of object features improve the user's prediction of the model's competencies." @default.
- W3039731725 created "2020-07-10" @default.
- W3039731725 creator A5015965173 @default.
- W3039731725 creator A5052203401 @default.
- W3039731725 creator A5065379518 @default.
- W3039731725 creator A5068342884 @default.
- W3039731725 creator A5080488836 @default.
- W3039731725 creator A5083014172 @default.
- W3039731725 date "2020-07-02" @default.
- W3039731725 modified "2023-09-27" @default.
- W3039731725 title "The Impact of Explanations on AI Competency Prediction in VQA" @default.
- W3039731725 cites W1580868288 @default.
- W3039731725 cites W1585983533 @default.
- W3039731725 cites W1849277567 @default.
- W3039731725 cites W188378287 @default.
- W3039731725 cites W1933349210 @default.
- W3039731725 cites W2010360420 @default.
- W3039731725 cites W2116354394 @default.
- W3039731725 cites W2123344105 @default.
- W3039731725 cites W2156523753 @default.
- W3039731725 cites W2168747479 @default.
- W3039731725 cites W2250539671 @default.
- W3039731725 cites W2282821441 @default.
- W3039731725 cites W2332488709 @default.
- W3039731725 cites W2412400526 @default.
- W3039731725 cites W2560730294 @default.
- W3039731725 cites W2605369869 @default.
- W3039731725 cites W2608030593 @default.
- W3039731725 cites W2745461083 @default.
- W3039731725 cites W2785327160 @default.
- W3039731725 cites W2787119853 @default.
- W3039731725 cites W2883512601 @default.
- W3039731725 cites W2884093133 @default.
- W3039731725 cites W2887978863 @default.
- W3039731725 cites W2914029945 @default.
- W3039731725 cites W2934080415 @default.
- W3039731725 cites W2949690500 @default.
- W3039731725 cites W2950761309 @default.
- W3039731725 cites W2955198300 @default.
- W3039731725 cites W2962858109 @default.
- W3039731725 cites W2962884579 @default.
- W3039731725 cites W2963115613 @default.
- W3039731725 cites W2963341956 @default.
- W3039731725 cites W2963609017 @default.
- W3039731725 cites W2963628945 @default.
- W3039731725 cites W2963656855 @default.
- W3039731725 cites W2963668159 @default.
- W3039731725 cites W2963847595 @default.
- W3039731725 cites W2963954913 @default.
- W3039731725 cites W2964345214 @default.
- W3039731725 cites W2964350391 @default.
- W3039731725 cites W2972718810 @default.
- W3039731725 cites W2979382951 @default.
- W3039731725 cites W3006819444 @default.
- W3039731725 cites W3098054859 @default.
- W3039731725 cites W639708223 @default.
- W3039731725 cites W3101716639 @default.
- W3039731725 hasPublicationYear "2020" @default.
- W3039731725 type Work @default.
- W3039731725 sameAs 3039731725 @default.
- W3039731725 citedByCount "0" @default.
- W3039731725 crossrefType "posted-content" @default.
- W3039731725 hasAuthorship W3039731725A5015965173 @default.
- W3039731725 hasAuthorship W3039731725A5052203401 @default.
- W3039731725 hasAuthorship W3039731725A5065379518 @default.
- W3039731725 hasAuthorship W3039731725A5068342884 @default.
- W3039731725 hasAuthorship W3039731725A5080488836 @default.
- W3039731725 hasAuthorship W3039731725A5083014172 @default.
- W3039731725 hasConcept C107457646 @default.
- W3039731725 hasConcept C114614502 @default.
- W3039731725 hasConcept C119857082 @default.
- W3039731725 hasConcept C124952713 @default.
- W3039731725 hasConcept C127413603 @default.
- W3039731725 hasConcept C134306372 @default.
- W3039731725 hasConcept C142362112 @default.
- W3039731725 hasConcept C154945302 @default.
- W3039731725 hasConcept C15744967 @default.
- W3039731725 hasConcept C164226766 @default.
- W3039731725 hasConcept C169760540 @default.
- W3039731725 hasConcept C201995342 @default.
- W3039731725 hasConcept C26517878 @default.
- W3039731725 hasConcept C26760741 @default.
- W3039731725 hasConcept C2778120072 @default.
- W3039731725 hasConcept C2780451532 @default.
- W3039731725 hasConcept C2781238097 @default.
- W3039731725 hasConcept C33923547 @default.
- W3039731725 hasConcept C36503486 @default.
- W3039731725 hasConcept C38652104 @default.
- W3039731725 hasConcept C41008148 @default.
- W3039731725 hasConceptScore W3039731725C107457646 @default.
- W3039731725 hasConceptScore W3039731725C114614502 @default.
- W3039731725 hasConceptScore W3039731725C119857082 @default.
- W3039731725 hasConceptScore W3039731725C124952713 @default.
- W3039731725 hasConceptScore W3039731725C127413603 @default.
- W3039731725 hasConceptScore W3039731725C134306372 @default.
- W3039731725 hasConceptScore W3039731725C142362112 @default.
- W3039731725 hasConceptScore W3039731725C154945302 @default.
- W3039731725 hasConceptScore W3039731725C15744967 @default.
- W3039731725 hasConceptScore W3039731725C164226766 @default.
- W3039731725 hasConceptScore W3039731725C169760540 @default.