Matches in SemOpenAlex for { <https://semopenalex.org/work/W2471094925> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2471094925 endingPage "739" @default.
- W2471094925 startingPage "727" @default.
- W2471094925 abstract "Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to perform “reasoning”. Furthermore, for the task of multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model receives the answer as input and predicts whether or not an image-question-answer triplet is correct. We evaluate our model on the Visual7W Telling and the VQA Real Multiple Choice tasks, and find that even simple versions of our model perform competitively. Our best model achieves state-of-the-art performance of $$65.8,%$$ accuracy on the Visual7W Telling task and compares surprisingly well with the most complex systems proposed for the VQA Real Multiple Choice task. Additionally, we explore variants of the model and study the transferability of the model between both datasets. We also present an error analysis of our best model, the results of which suggest that a key problem of current VQA systems lies in the lack of visual grounding and localization of concepts that occur in the questions and answers." @default.
- W2471094925 created "2016-07-22" @default.
- W2471094925 creator A5030266788 @default.
- W2471094925 creator A5041693326 @default.
- W2471094925 creator A5081649142 @default.
- W2471094925 date "2016-01-01" @default.
- W2471094925 modified "2023-10-12" @default.
- W2471094925 title "Revisiting Visual Question Answering Baselines" @default.
- W2471094925 cites W102708294 @default.
- W2471094925 cites W1861492603 @default.
- W2471094925 cites W1933349210 @default.
- W2471094925 cites W1983927101 @default.
- W2471094925 cites W2062118960 @default.
- W2471094925 cites W2064675550 @default.
- W2471094925 cites W2097117768 @default.
- W2471094925 cites W2100031962 @default.
- W2471094925 cites W2142192571 @default.
- W2471094925 cites W2194775991 @default.
- W2471094925 cites W2202226326 @default.
- W2471094925 cites W2277195237 @default.
- W2471094925 cites W2962749469 @default.
- W2471094925 cites W2963191264 @default.
- W2471094925 cites W2963383024 @default.
- W2471094925 cites W2963672682 @default.
- W2471094925 cites W2963954913 @default.
- W2471094925 cites W2964118342 @default.
- W2471094925 cites W3037725825 @default.
- W2471094925 doi "https://doi.org/10.1007/978-3-319-46484-8_44" @default.
- W2471094925 hasPublicationYear "2016" @default.
- W2471094925 type Work @default.
- W2471094925 sameAs 2471094925 @default.
- W2471094925 citedByCount "163" @default.
- W2471094925 countsByYear W24710949252016 @default.
- W2471094925 countsByYear W24710949252017 @default.
- W2471094925 countsByYear W24710949252018 @default.
- W2471094925 countsByYear W24710949252019 @default.
- W2471094925 countsByYear W24710949252020 @default.
- W2471094925 countsByYear W24710949252021 @default.
- W2471094925 countsByYear W24710949252022 @default.
- W2471094925 countsByYear W24710949252023 @default.
- W2471094925 crossrefType "book-chapter" @default.
- W2471094925 hasAuthorship W2471094925A5030266788 @default.
- W2471094925 hasAuthorship W2471094925A5041693326 @default.
- W2471094925 hasAuthorship W2471094925A5081649142 @default.
- W2471094925 hasBestOaLocation W24710949252 @default.
- W2471094925 hasConcept C111472728 @default.
- W2471094925 hasConcept C119857082 @default.
- W2471094925 hasConcept C12267149 @default.
- W2471094925 hasConcept C138885662 @default.
- W2471094925 hasConcept C140331021 @default.
- W2471094925 hasConcept C154945302 @default.
- W2471094925 hasConcept C162324750 @default.
- W2471094925 hasConcept C187736073 @default.
- W2471094925 hasConcept C2777508537 @default.
- W2471094925 hasConcept C2780451532 @default.
- W2471094925 hasConcept C2780586882 @default.
- W2471094925 hasConcept C41008148 @default.
- W2471094925 hasConcept C44291984 @default.
- W2471094925 hasConcept C61272859 @default.
- W2471094925 hasConcept C66905080 @default.
- W2471094925 hasConcept C95623464 @default.
- W2471094925 hasConceptScore W2471094925C111472728 @default.
- W2471094925 hasConceptScore W2471094925C119857082 @default.
- W2471094925 hasConceptScore W2471094925C12267149 @default.
- W2471094925 hasConceptScore W2471094925C138885662 @default.
- W2471094925 hasConceptScore W2471094925C140331021 @default.
- W2471094925 hasConceptScore W2471094925C154945302 @default.
- W2471094925 hasConceptScore W2471094925C162324750 @default.
- W2471094925 hasConceptScore W2471094925C187736073 @default.
- W2471094925 hasConceptScore W2471094925C2777508537 @default.
- W2471094925 hasConceptScore W2471094925C2780451532 @default.
- W2471094925 hasConceptScore W2471094925C2780586882 @default.
- W2471094925 hasConceptScore W2471094925C41008148 @default.
- W2471094925 hasConceptScore W2471094925C44291984 @default.
- W2471094925 hasConceptScore W2471094925C61272859 @default.
- W2471094925 hasConceptScore W2471094925C66905080 @default.
- W2471094925 hasConceptScore W2471094925C95623464 @default.
- W2471094925 hasLocation W24710949251 @default.
- W2471094925 hasLocation W24710949252 @default.
- W2471094925 hasOpenAccess W2471094925 @default.
- W2471094925 hasPrimaryLocation W24710949251 @default.
- W2471094925 hasRelatedWork W2121061354 @default.
- W2471094925 hasRelatedWork W2231285690 @default.
- W2471094925 hasRelatedWork W2438464946 @default.
- W2471094925 hasRelatedWork W2496096353 @default.
- W2471094925 hasRelatedWork W2553418567 @default.
- W2471094925 hasRelatedWork W2963477107 @default.
- W2471094925 hasRelatedWork W2964061310 @default.
- W2471094925 hasRelatedWork W3045060014 @default.
- W2471094925 hasRelatedWork W4285388059 @default.
- W2471094925 hasRelatedWork W4382934300 @default.
- W2471094925 isParatext "false" @default.
- W2471094925 isRetracted "false" @default.
- W2471094925 magId "2471094925" @default.
- W2471094925 workType "book-chapter" @default.