Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200633461> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4200633461 abstract "Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 2,000+ videos with more than 1,750,000+ frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 30+ open categories with a wide selection of various scenarios, e.g., Life Vlog, Driving, Movie, etc. Thirdly, abundant text types annotation (i.e., title, caption or scene text) are provided for the different representational meanings in video. Fourthly, the BOVText provides bilingual text annotation to promote multiple cultures live and communication. Besides, we propose an end-to-end video text spotting framework with Transformer, termed TransVTSpotter, which solves the multi-orient text spotting in video with a simple, but efficient attention-based query-key mechanism. It applies object features from the previous frame as a tracking query for the current frame and introduces a rotation angle prediction to fit the multiorient text instance. On ICDAR2015(video), TransVTSpotter achieves the state-of-the-art performance with 44.1% MOTA, 9 fps. The dataset and code of TransVTSpotter can be found at github:com=weijiawu=BOVText and github:com=weijiawu=TransVTSpotter, respectively." @default.
- W4200633461 created "2021-12-31" @default.
- W4200633461 creator A5001831754 @default.
- W4200633461 creator A5011779639 @default.
- W4200633461 creator A5019444857 @default.
- W4200633461 creator A5029304001 @default.
- W4200633461 creator A5034584642 @default.
- W4200633461 creator A5047839791 @default.
- W4200633461 creator A5066759526 @default.
- W4200633461 creator A5069785885 @default.
- W4200633461 date "2021-12-09" @default.
- W4200633461 modified "2023-10-18" @default.
- W4200633461 title "A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer" @default.
- W4200633461 doi "https://doi.org/10.48550/arxiv.2112.04888" @default.
- W4200633461 hasPublicationYear "2021" @default.
- W4200633461 type Work @default.
- W4200633461 citedByCount "0" @default.
- W4200633461 crossrefType "posted-content" @default.
- W4200633461 hasAuthorship W4200633461A5001831754 @default.
- W4200633461 hasAuthorship W4200633461A5011779639 @default.
- W4200633461 hasAuthorship W4200633461A5019444857 @default.
- W4200633461 hasAuthorship W4200633461A5029304001 @default.
- W4200633461 hasAuthorship W4200633461A5034584642 @default.
- W4200633461 hasAuthorship W4200633461A5047839791 @default.
- W4200633461 hasAuthorship W4200633461A5066759526 @default.
- W4200633461 hasAuthorship W4200633461A5069785885 @default.
- W4200633461 hasBestOaLocation W42006334611 @default.
- W4200633461 hasConcept C111919701 @default.
- W4200633461 hasConcept C118505674 @default.
- W4200633461 hasConcept C121332964 @default.
- W4200633461 hasConcept C13280743 @default.
- W4200633461 hasConcept C154945302 @default.
- W4200633461 hasConcept C165801399 @default.
- W4200633461 hasConcept C185798385 @default.
- W4200633461 hasConcept C202474056 @default.
- W4200633461 hasConcept C204321447 @default.
- W4200633461 hasConcept C205649164 @default.
- W4200633461 hasConcept C23123220 @default.
- W4200633461 hasConcept C2776321320 @default.
- W4200633461 hasConcept C2779506182 @default.
- W4200633461 hasConcept C2781238097 @default.
- W4200633461 hasConcept C41008148 @default.
- W4200633461 hasConcept C62520636 @default.
- W4200633461 hasConcept C66322947 @default.
- W4200633461 hasConcept C74296488 @default.
- W4200633461 hasConceptScore W4200633461C111919701 @default.
- W4200633461 hasConceptScore W4200633461C118505674 @default.
- W4200633461 hasConceptScore W4200633461C121332964 @default.
- W4200633461 hasConceptScore W4200633461C13280743 @default.
- W4200633461 hasConceptScore W4200633461C154945302 @default.
- W4200633461 hasConceptScore W4200633461C165801399 @default.
- W4200633461 hasConceptScore W4200633461C185798385 @default.
- W4200633461 hasConceptScore W4200633461C202474056 @default.
- W4200633461 hasConceptScore W4200633461C204321447 @default.
- W4200633461 hasConceptScore W4200633461C205649164 @default.
- W4200633461 hasConceptScore W4200633461C23123220 @default.
- W4200633461 hasConceptScore W4200633461C2776321320 @default.
- W4200633461 hasConceptScore W4200633461C2779506182 @default.
- W4200633461 hasConceptScore W4200633461C2781238097 @default.
- W4200633461 hasConceptScore W4200633461C41008148 @default.
- W4200633461 hasConceptScore W4200633461C62520636 @default.
- W4200633461 hasConceptScore W4200633461C66322947 @default.
- W4200633461 hasConceptScore W4200633461C74296488 @default.
- W4200633461 hasLocation W42006334611 @default.
- W4200633461 hasLocation W42006334612 @default.
- W4200633461 hasOpenAccess W4200633461 @default.
- W4200633461 hasPrimaryLocation W42006334611 @default.
- W4200633461 hasRelatedWork W1487175407 @default.
- W4200633461 hasRelatedWork W2068395580 @default.
- W4200633461 hasRelatedWork W2187223183 @default.
- W4200633461 hasRelatedWork W2291627510 @default.
- W4200633461 hasRelatedWork W2385949326 @default.
- W4200633461 hasRelatedWork W2422898642 @default.
- W4200633461 hasRelatedWork W2789220062 @default.
- W4200633461 hasRelatedWork W3163605596 @default.
- W4200633461 hasRelatedWork W3177406559 @default.
- W4200633461 hasRelatedWork W3210438479 @default.
- W4200633461 isParatext "false" @default.
- W4200633461 isRetracted "false" @default.
- W4200633461 workType "article" @default.