Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313409510> ?p ?o ?g. }
- W4313409510 endingPage "159" @default.
- W4313409510 startingPage "159" @default.
- W4313409510 abstract "Text detection has been significantly boosted by the development of deep neural networks but most existing methods focus on a single kind of text instance (i.e., overlaid text, layered text, scene text). In this paper, we expand the text detection task from a single dimension to multiple dimensions, thus providing multi-type text descriptions for the scene and content analysis of videos. Specifically, we establish a new task to detect and classify text instances simultaneously, termed TextDC. As far as we know, existing benchmarks cannot meet the requirements of the proposed task. To this end, we collect a large-scale text detection and classification dataset, named Text3C, which is annotated using multilingual labels, location information, and text categories. Together with the collected dataset, we introduce a multi-stage and strict evaluation metric, which penalizes detection approaches for missing text instances, false positive detection, inaccurate location boxes, and error text categories, developing a new benchmark for the proposed TextDC task. In addition, we extend several state-of-the-art detectors by modifying the prediction head to solve the new task. Then, a generalized text detection and classification framework is designed and formulated. Extensive experiments using the updated methods are conducted on the established benchmark to verify the solvability of the proposed task, the challenges of the dataset, and the effectiveness of the solution." @default.
- W4313409510 created "2023-01-06" @default.
- W4313409510 creator A5006146330 @default.
- W4313409510 creator A5026883089 @default.
- W4313409510 creator A5079137368 @default.
- W4313409510 date "2022-12-29" @default.
- W4313409510 modified "2023-10-05" @default.
- W4313409510 title "TextDC: Exploring Multidimensional Text Detection via a New Benchmark and Solution" @default.
- W4313409510 cites W1861492603 @default.
- W4313409510 cites W1966631307 @default.
- W4313409510 cites W2008806374 @default.
- W4313409510 cites W2014286161 @default.
- W4313409510 cites W2118519743 @default.
- W4313409510 cites W2135231474 @default.
- W4313409510 cites W2142380309 @default.
- W4313409510 cites W2144554289 @default.
- W4313409510 cites W2145020494 @default.
- W4313409510 cites W2194775991 @default.
- W4313409510 cites W2340583188 @default.
- W4313409510 cites W2436394148 @default.
- W4313409510 cites W2550687635 @default.
- W4313409510 cites W2565639579 @default.
- W4313409510 cites W2594435365 @default.
- W4313409510 cites W2605982830 @default.
- W4313409510 cites W2606394513 @default.
- W4313409510 cites W2785383245 @default.
- W4313409510 cites W2807605148 @default.
- W4313409510 cites W2914492226 @default.
- W4313409510 cites W2945136398 @default.
- W4313409510 cites W2963195262 @default.
- W4313409510 cites W2963647456 @default.
- W4313409510 cites W2963840241 @default.
- W4313409510 cites W2964294787 @default.
- W4313409510 cites W2965463054 @default.
- W4313409510 cites W2998621280 @default.
- W4313409510 cites W3002706982 @default.
- W4313409510 cites W3003868038 @default.
- W4313409510 cites W3003921261 @default.
- W4313409510 cites W3009262022 @default.
- W4313409510 cites W3034514377 @default.
- W4313409510 cites W3034792612 @default.
- W4313409510 cites W3082397598 @default.
- W4313409510 cites W3092156752 @default.
- W4313409510 cites W3093046205 @default.
- W4313409510 cites W3171030392 @default.
- W4313409510 cites W3181016597 @default.
- W4313409510 cites W3184364189 @default.
- W4313409510 cites W4225683503 @default.
- W4313409510 cites W4312593844 @default.
- W4313409510 cites W654550266 @default.
- W4313409510 doi "https://doi.org/10.3390/electronics12010159" @default.
- W4313409510 hasPublicationYear "2022" @default.
- W4313409510 type Work @default.
- W4313409510 citedByCount "0" @default.
- W4313409510 crossrefType "journal-article" @default.
- W4313409510 hasAuthorship W4313409510A5006146330 @default.
- W4313409510 hasAuthorship W4313409510A5026883089 @default.
- W4313409510 hasAuthorship W4313409510A5079137368 @default.
- W4313409510 hasBestOaLocation W43134095101 @default.
- W4313409510 hasConcept C119857082 @default.
- W4313409510 hasConcept C120665830 @default.
- W4313409510 hasConcept C121332964 @default.
- W4313409510 hasConcept C124101348 @default.
- W4313409510 hasConcept C13280743 @default.
- W4313409510 hasConcept C153180895 @default.
- W4313409510 hasConcept C154945302 @default.
- W4313409510 hasConcept C162324750 @default.
- W4313409510 hasConcept C176217482 @default.
- W4313409510 hasConcept C185798385 @default.
- W4313409510 hasConcept C187736073 @default.
- W4313409510 hasConcept C192209626 @default.
- W4313409510 hasConcept C202444582 @default.
- W4313409510 hasConcept C204321447 @default.
- W4313409510 hasConcept C205649164 @default.
- W4313409510 hasConcept C21547014 @default.
- W4313409510 hasConcept C23123220 @default.
- W4313409510 hasConcept C2780451532 @default.
- W4313409510 hasConcept C33676613 @default.
- W4313409510 hasConcept C33923547 @default.
- W4313409510 hasConcept C41008148 @default.
- W4313409510 hasConceptScore W4313409510C119857082 @default.
- W4313409510 hasConceptScore W4313409510C120665830 @default.
- W4313409510 hasConceptScore W4313409510C121332964 @default.
- W4313409510 hasConceptScore W4313409510C124101348 @default.
- W4313409510 hasConceptScore W4313409510C13280743 @default.
- W4313409510 hasConceptScore W4313409510C153180895 @default.
- W4313409510 hasConceptScore W4313409510C154945302 @default.
- W4313409510 hasConceptScore W4313409510C162324750 @default.
- W4313409510 hasConceptScore W4313409510C176217482 @default.
- W4313409510 hasConceptScore W4313409510C185798385 @default.
- W4313409510 hasConceptScore W4313409510C187736073 @default.
- W4313409510 hasConceptScore W4313409510C192209626 @default.
- W4313409510 hasConceptScore W4313409510C202444582 @default.
- W4313409510 hasConceptScore W4313409510C204321447 @default.
- W4313409510 hasConceptScore W4313409510C205649164 @default.
- W4313409510 hasConceptScore W4313409510C21547014 @default.
- W4313409510 hasConceptScore W4313409510C23123220 @default.
- W4313409510 hasConceptScore W4313409510C2780451532 @default.