Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378473755> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4378473755 abstract "Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks. However, such generalization to vision-language tasks including grounding and generation tasks has been under-explored; existing few-shot VL models struggle to handle tasks that involve object grounding and multiple images such as visual commonsense reasoning or NLVR2. In this paper, we introduce GRILL, GRounded vIsion Language aLigning, a novel VL model that can be generalized to diverse tasks including visual question answering, captioning, and grounding tasks with no or very few training instances. Specifically, GRILL learns object grounding and localization by exploiting object-text alignments, which enables it to transfer to grounding tasks in a zero-/few-shot fashion. We evaluate our model on various zero-/few-shot VL tasks and show that it consistently surpasses the state-of-the-art few-shot methods." @default.
- W4378473755 created "2023-05-27" @default.
- W4378473755 creator A5009408707 @default.
- W4378473755 creator A5021000040 @default.
- W4378473755 creator A5026746295 @default.
- W4378473755 creator A5033994052 @default.
- W4378473755 creator A5043356063 @default.
- W4378473755 creator A5051745436 @default.
- W4378473755 creator A5083082697 @default.
- W4378473755 creator A5087823830 @default.
- W4378473755 date "2023-05-23" @default.
- W4378473755 modified "2023-10-16" @default.
- W4378473755 title "GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions" @default.
- W4378473755 doi "https://doi.org/10.48550/arxiv.2305.14676" @default.
- W4378473755 hasPublicationYear "2023" @default.
- W4378473755 type Work @default.
- W4378473755 citedByCount "0" @default.
- W4378473755 crossrefType "posted-content" @default.
- W4378473755 hasAuthorship W4378473755A5009408707 @default.
- W4378473755 hasAuthorship W4378473755A5021000040 @default.
- W4378473755 hasAuthorship W4378473755A5026746295 @default.
- W4378473755 hasAuthorship W4378473755A5033994052 @default.
- W4378473755 hasAuthorship W4378473755A5043356063 @default.
- W4378473755 hasAuthorship W4378473755A5051745436 @default.
- W4378473755 hasAuthorship W4378473755A5083082697 @default.
- W4378473755 hasAuthorship W4378473755A5087823830 @default.
- W4378473755 hasBestOaLocation W43784737551 @default.
- W4378473755 hasConcept C115961682 @default.
- W4378473755 hasConcept C121332964 @default.
- W4378473755 hasConcept C127413603 @default.
- W4378473755 hasConcept C134306372 @default.
- W4378473755 hasConcept C137293760 @default.
- W4378473755 hasConcept C154945302 @default.
- W4378473755 hasConcept C157657479 @default.
- W4378473755 hasConcept C168993435 @default.
- W4378473755 hasConcept C177148314 @default.
- W4378473755 hasConcept C178790620 @default.
- W4378473755 hasConcept C185592680 @default.
- W4378473755 hasConcept C204321447 @default.
- W4378473755 hasConcept C2778344882 @default.
- W4378473755 hasConcept C2781238097 @default.
- W4378473755 hasConcept C2992734406 @default.
- W4378473755 hasConcept C31972630 @default.
- W4378473755 hasConcept C33923547 @default.
- W4378473755 hasConcept C41008148 @default.
- W4378473755 hasConcept C62520636 @default.
- W4378473755 hasConcept C78519656 @default.
- W4378473755 hasConceptScore W4378473755C115961682 @default.
- W4378473755 hasConceptScore W4378473755C121332964 @default.
- W4378473755 hasConceptScore W4378473755C127413603 @default.
- W4378473755 hasConceptScore W4378473755C134306372 @default.
- W4378473755 hasConceptScore W4378473755C137293760 @default.
- W4378473755 hasConceptScore W4378473755C154945302 @default.
- W4378473755 hasConceptScore W4378473755C157657479 @default.
- W4378473755 hasConceptScore W4378473755C168993435 @default.
- W4378473755 hasConceptScore W4378473755C177148314 @default.
- W4378473755 hasConceptScore W4378473755C178790620 @default.
- W4378473755 hasConceptScore W4378473755C185592680 @default.
- W4378473755 hasConceptScore W4378473755C204321447 @default.
- W4378473755 hasConceptScore W4378473755C2778344882 @default.
- W4378473755 hasConceptScore W4378473755C2781238097 @default.
- W4378473755 hasConceptScore W4378473755C2992734406 @default.
- W4378473755 hasConceptScore W4378473755C31972630 @default.
- W4378473755 hasConceptScore W4378473755C33923547 @default.
- W4378473755 hasConceptScore W4378473755C41008148 @default.
- W4378473755 hasConceptScore W4378473755C62520636 @default.
- W4378473755 hasConceptScore W4378473755C78519656 @default.
- W4378473755 hasLocation W43784737551 @default.
- W4378473755 hasOpenAccess W4378473755 @default.
- W4378473755 hasPrimaryLocation W43784737551 @default.
- W4378473755 hasRelatedWork W1837097281 @default.
- W4378473755 hasRelatedWork W1966410754 @default.
- W4378473755 hasRelatedWork W2007544051 @default.
- W4378473755 hasRelatedWork W2092957489 @default.
- W4378473755 hasRelatedWork W2795359650 @default.
- W4378473755 hasRelatedWork W2923366293 @default.
- W4378473755 hasRelatedWork W2975200075 @default.
- W4378473755 hasRelatedWork W3008515501 @default.
- W4378473755 hasRelatedWork W3102877762 @default.
- W4378473755 hasRelatedWork W4307928143 @default.
- W4378473755 isParatext "false" @default.
- W4378473755 isRetracted "false" @default.
- W4378473755 workType "article" @default.