Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306809100> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4306809100 abstract "This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years. We group these approaches into three categories: ($i$) VLP for image-text tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding; ($ii$) VLP for core computer vision tasks, such as (open-set) image classification, object detection, and segmentation; and ($iii$) VLP for video-text tasks, such as video captioning, video-text retrieval, and video question answering. For each category, we present a comprehensive review of state-of-the-art methods, and discuss the progress that has been made and challenges still being faced, using specific systems and models as case studies. In addition, for each category, we discuss advanced topics being actively explored in the research community, such as big foundation models, unified modeling, in-context few-shot learning, knowledge, robustness, and computer vision in the wild, to name a few." @default.
- W4306809100 created "2022-10-20" @default.
- W4306809100 creator A5003075563 @default.
- W4306809100 creator A5028783832 @default.
- W4306809100 creator A5047233371 @default.
- W4306809100 creator A5048295582 @default.
- W4306809100 creator A5066666034 @default.
- W4306809100 creator A5073435344 @default.
- W4306809100 date "2022-10-17" @default.
- W4306809100 modified "2023-10-17" @default.
- W4306809100 title "Vision-Language Pre-training: Basics, Recent Advances, and Future Trends" @default.
- W4306809100 doi "https://doi.org/10.48550/arxiv.2210.09263" @default.
- W4306809100 hasPublicationYear "2022" @default.
- W4306809100 type Work @default.
- W4306809100 citedByCount "0" @default.
- W4306809100 crossrefType "posted-content" @default.
- W4306809100 hasAuthorship W4306809100A5003075563 @default.
- W4306809100 hasAuthorship W4306809100A5028783832 @default.
- W4306809100 hasAuthorship W4306809100A5047233371 @default.
- W4306809100 hasAuthorship W4306809100A5048295582 @default.
- W4306809100 hasAuthorship W4306809100A5066666034 @default.
- W4306809100 hasAuthorship W4306809100A5073435344 @default.
- W4306809100 hasBestOaLocation W43068091001 @default.
- W4306809100 hasConcept C115961682 @default.
- W4306809100 hasConcept C151730666 @default.
- W4306809100 hasConcept C154945302 @default.
- W4306809100 hasConcept C157657479 @default.
- W4306809100 hasConcept C204321447 @default.
- W4306809100 hasConcept C2779343474 @default.
- W4306809100 hasConcept C2983174267 @default.
- W4306809100 hasConcept C41008148 @default.
- W4306809100 hasConcept C44291984 @default.
- W4306809100 hasConcept C49774154 @default.
- W4306809100 hasConcept C86803240 @default.
- W4306809100 hasConceptScore W4306809100C115961682 @default.
- W4306809100 hasConceptScore W4306809100C151730666 @default.
- W4306809100 hasConceptScore W4306809100C154945302 @default.
- W4306809100 hasConceptScore W4306809100C157657479 @default.
- W4306809100 hasConceptScore W4306809100C204321447 @default.
- W4306809100 hasConceptScore W4306809100C2779343474 @default.
- W4306809100 hasConceptScore W4306809100C2983174267 @default.
- W4306809100 hasConceptScore W4306809100C41008148 @default.
- W4306809100 hasConceptScore W4306809100C44291984 @default.
- W4306809100 hasConceptScore W4306809100C49774154 @default.
- W4306809100 hasConceptScore W4306809100C86803240 @default.
- W4306809100 hasLocation W43068091001 @default.
- W4306809100 hasOpenAccess W4306809100 @default.
- W4306809100 hasPrimaryLocation W43068091001 @default.
- W4306809100 hasRelatedWork W1517743118 @default.
- W4306809100 hasRelatedWork W1518289136 @default.
- W4306809100 hasRelatedWork W1527340856 @default.
- W4306809100 hasRelatedWork W1560657467 @default.
- W4306809100 hasRelatedWork W1852167757 @default.
- W4306809100 hasRelatedWork W207304934 @default.
- W4306809100 hasRelatedWork W2364913186 @default.
- W4306809100 hasRelatedWork W2747680751 @default.
- W4306809100 hasRelatedWork W4320016117 @default.
- W4306809100 hasRelatedWork W4377703168 @default.
- W4306809100 isParatext "false" @default.
- W4306809100 isRetracted "false" @default.
- W4306809100 workType "article" @default.