Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385688545> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4385688545 abstract "This paper studies a category of visual question answering tasks, in which accessing external knowledge is necessary for answering the questions. This category is called outside-knowledge visual question answering (OK-VQA). A major step in developing OK-VQA systems is to retrieve relevant documents for the given multi-modal query. Current state-of-the-art asymmetric dense retrieval model for this task uses an architecture with a multi-modal query encoder and a uni-modal document encoder. Such an architecture requires a large amount of training data for effective performance. We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks. The proposed approach leads to 26.9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture. Additionally, the proposed pre-training approach exhibits a good ability in zero-shot retrieval scenarios." @default.
- W4385688545 created "2023-08-10" @default.
- W4385688545 creator A5014088751 @default.
- W4385688545 creator A5031589474 @default.
- W4385688545 creator A5082594835 @default.
- W4385688545 date "2023-08-09" @default.
- W4385688545 modified "2023-09-26" @default.
- W4385688545 title "Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering" @default.
- W4385688545 cites W1861492603 @default.
- W4385688545 cites W2963323070 @default.
- W4385688545 cites W2963748441 @default.
- W4385688545 cites W2964303913 @default.
- W4385688545 cites W2970231061 @default.
- W4385688545 cites W2998536339 @default.
- W4385688545 cites W2998702515 @default.
- W4385688545 cites W3035313607 @default.
- W4385688545 cites W3099700870 @default.
- W4385688545 cites W3139224848 @default.
- W4385688545 cites W3156082048 @default.
- W4385688545 cites W4200635123 @default.
- W4385688545 cites W4205888310 @default.
- W4385688545 cites W4226292322 @default.
- W4385688545 cites W4226321975 @default.
- W4385688545 cites W4283777642 @default.
- W4385688545 cites W4284669679 @default.
- W4385688545 cites W4287887134 @default.
- W4385688545 cites W4385573917 @default.
- W4385688545 doi "https://doi.org/10.1145/3578337.3605137" @default.
- W4385688545 hasPublicationYear "2023" @default.
- W4385688545 type Work @default.
- W4385688545 citedByCount "0" @default.
- W4385688545 crossrefType "proceedings-article" @default.
- W4385688545 hasAuthorship W4385688545A5014088751 @default.
- W4385688545 hasAuthorship W4385688545A5031589474 @default.
- W4385688545 hasAuthorship W4385688545A5082594835 @default.
- W4385688545 hasBestOaLocation W43856885451 @default.
- W4385688545 hasConcept C111919701 @default.
- W4385688545 hasConcept C118505674 @default.
- W4385688545 hasConcept C123657996 @default.
- W4385688545 hasConcept C142362112 @default.
- W4385688545 hasConcept C153349607 @default.
- W4385688545 hasConcept C154945302 @default.
- W4385688545 hasConcept C162324750 @default.
- W4385688545 hasConcept C185592680 @default.
- W4385688545 hasConcept C187736073 @default.
- W4385688545 hasConcept C188027245 @default.
- W4385688545 hasConcept C199360897 @default.
- W4385688545 hasConcept C204321447 @default.
- W4385688545 hasConcept C23123220 @default.
- W4385688545 hasConcept C2780451532 @default.
- W4385688545 hasConcept C41008148 @default.
- W4385688545 hasConcept C43521106 @default.
- W4385688545 hasConcept C44291984 @default.
- W4385688545 hasConcept C51632099 @default.
- W4385688545 hasConcept C71139939 @default.
- W4385688545 hasConceptScore W4385688545C111919701 @default.
- W4385688545 hasConceptScore W4385688545C118505674 @default.
- W4385688545 hasConceptScore W4385688545C123657996 @default.
- W4385688545 hasConceptScore W4385688545C142362112 @default.
- W4385688545 hasConceptScore W4385688545C153349607 @default.
- W4385688545 hasConceptScore W4385688545C154945302 @default.
- W4385688545 hasConceptScore W4385688545C162324750 @default.
- W4385688545 hasConceptScore W4385688545C185592680 @default.
- W4385688545 hasConceptScore W4385688545C187736073 @default.
- W4385688545 hasConceptScore W4385688545C188027245 @default.
- W4385688545 hasConceptScore W4385688545C199360897 @default.
- W4385688545 hasConceptScore W4385688545C204321447 @default.
- W4385688545 hasConceptScore W4385688545C23123220 @default.
- W4385688545 hasConceptScore W4385688545C2780451532 @default.
- W4385688545 hasConceptScore W4385688545C41008148 @default.
- W4385688545 hasConceptScore W4385688545C43521106 @default.
- W4385688545 hasConceptScore W4385688545C44291984 @default.
- W4385688545 hasConceptScore W4385688545C51632099 @default.
- W4385688545 hasConceptScore W4385688545C71139939 @default.
- W4385688545 hasLocation W43856885451 @default.
- W4385688545 hasLocation W43856885452 @default.
- W4385688545 hasOpenAccess W4385688545 @default.
- W4385688545 hasPrimaryLocation W43856885451 @default.
- W4385688545 hasRelatedWork W1560657467 @default.
- W4385688545 hasRelatedWork W2020540721 @default.
- W4385688545 hasRelatedWork W2051167396 @default.
- W4385688545 hasRelatedWork W207304934 @default.
- W4385688545 hasRelatedWork W219090214 @default.
- W4385688545 hasRelatedWork W2578916128 @default.
- W4385688545 hasRelatedWork W2970044932 @default.
- W4385688545 hasRelatedWork W3210635025 @default.
- W4385688545 hasRelatedWork W4285236007 @default.
- W4385688545 hasRelatedWork W4377703168 @default.
- W4385688545 isParatext "false" @default.
- W4385688545 isRetracted "false" @default.
- W4385688545 workType "article" @default.