Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387635275> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4387635275 abstract "Given an image and an associated textual question, the purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases. Prior KB-VQA models are usually formulated as a retriever-classifier framework, where a pre-trained retriever extracts textual or visual information from knowledge graphs and then makes a prediction among the candidates. Despite promising progress, there are two drawbacks with existing models. Firstly, modeling question-answering as multi-class classification limits the answer space to a preset corpus and lacks the ability of flexible reasoning. Secondly, the classifier merely consider what is the answer without how to get the answer, which cannot ground the answer to explicit reasoning paths. In this paper, we confront the challenge of emph{explainable open-set} KB-VQA, where the system is required to answer questions with entities at wild and retain an explainable reasoning path. To resolve the aforementioned issues, we propose a new retriever-ranker paradigm of KB-VQA, Graph pATH rankER (GATHER for brevity). Specifically, it contains graph constructing, pruning, and path-level ranking, which not only retrieves accurate answers but also provides inference paths that explain the reasoning process. To comprehensively evaluate our model, we reformulate the benchmark dataset OK-VQA with manually corrected entity-level annotations and release it as ConceptVQA. Extensive experiments on real-world questions demonstrate that our framework is not only able to perform open-set question answering across the whole knowledge base but provide explicit reasoning path." @default.
- W4387635275 created "2023-10-14" @default.
- W4387635275 creator A5028597017 @default.
- W4387635275 creator A5034112897 @default.
- W4387635275 creator A5041272277 @default.
- W4387635275 creator A5049313711 @default.
- W4387635275 date "2023-10-12" @default.
- W4387635275 modified "2023-10-15" @default.
- W4387635275 title "Open-Set Knowledge-Based Visual Question Answering with Inference Paths" @default.
- W4387635275 doi "https://doi.org/10.48550/arxiv.2310.08148" @default.
- W4387635275 hasPublicationYear "2023" @default.
- W4387635275 type Work @default.
- W4387635275 citedByCount "0" @default.
- W4387635275 crossrefType "posted-content" @default.
- W4387635275 hasAuthorship W4387635275A5028597017 @default.
- W4387635275 hasAuthorship W4387635275A5034112897 @default.
- W4387635275 hasAuthorship W4387635275A5041272277 @default.
- W4387635275 hasAuthorship W4387635275A5049313711 @default.
- W4387635275 hasBestOaLocation W43876352751 @default.
- W4387635275 hasConcept C118615104 @default.
- W4387635275 hasConcept C119857082 @default.
- W4387635275 hasConcept C132525143 @default.
- W4387635275 hasConcept C154945302 @default.
- W4387635275 hasConcept C199360897 @default.
- W4387635275 hasConcept C23123220 @default.
- W4387635275 hasConcept C2776214188 @default.
- W4387635275 hasConcept C2777735758 @default.
- W4387635275 hasConcept C33923547 @default.
- W4387635275 hasConcept C41008148 @default.
- W4387635275 hasConcept C42357961 @default.
- W4387635275 hasConcept C44291984 @default.
- W4387635275 hasConcept C4554734 @default.
- W4387635275 hasConcept C80444323 @default.
- W4387635275 hasConcept C95623464 @default.
- W4387635275 hasConceptScore W4387635275C118615104 @default.
- W4387635275 hasConceptScore W4387635275C119857082 @default.
- W4387635275 hasConceptScore W4387635275C132525143 @default.
- W4387635275 hasConceptScore W4387635275C154945302 @default.
- W4387635275 hasConceptScore W4387635275C199360897 @default.
- W4387635275 hasConceptScore W4387635275C23123220 @default.
- W4387635275 hasConceptScore W4387635275C2776214188 @default.
- W4387635275 hasConceptScore W4387635275C2777735758 @default.
- W4387635275 hasConceptScore W4387635275C33923547 @default.
- W4387635275 hasConceptScore W4387635275C41008148 @default.
- W4387635275 hasConceptScore W4387635275C42357961 @default.
- W4387635275 hasConceptScore W4387635275C44291984 @default.
- W4387635275 hasConceptScore W4387635275C4554734 @default.
- W4387635275 hasConceptScore W4387635275C80444323 @default.
- W4387635275 hasConceptScore W4387635275C95623464 @default.
- W4387635275 hasLocation W43876352751 @default.
- W4387635275 hasOpenAccess W4387635275 @default.
- W4387635275 hasPrimaryLocation W43876352751 @default.
- W4387635275 hasRelatedWork W2136007095 @default.
- W4387635275 hasRelatedWork W2366230879 @default.
- W4387635275 hasRelatedWork W2384605597 @default.
- W4387635275 hasRelatedWork W2387743295 @default.
- W4387635275 hasRelatedWork W2442806191 @default.
- W4387635275 hasRelatedWork W3082787378 @default.
- W4387635275 hasRelatedWork W3134247745 @default.
- W4387635275 hasRelatedWork W3172691639 @default.
- W4387635275 hasRelatedWork W4226243593 @default.
- W4387635275 hasRelatedWork W4285816982 @default.
- W4387635275 isParatext "false" @default.
- W4387635275 isRetracted "false" @default.
- W4387635275 workType "article" @default.