Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175248253> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3175248253 abstract "The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance. Experiments prove that the proposed method achieves competitive accuracy, meanwhile significantly improving the running speed. In particular, in Total-Text, it runs at 46.7 FPS, surpassing the previous spotters with a large margin." @default.
- W3175248253 created "2021-07-05" @default.
- W3175248253 creator A5016467601 @default.
- W3175248253 creator A5022200044 @default.
- W3175248253 creator A5027156714 @default.
- W3175248253 creator A5050031109 @default.
- W3175248253 creator A5051125527 @default.
- W3175248253 creator A5062071376 @default.
- W3175248253 creator A5076375120 @default.
- W3175248253 creator A5076936566 @default.
- W3175248253 creator A5079904889 @default.
- W3175248253 creator A5080777665 @default.
- W3175248253 date "2021-04-12" @default.
- W3175248253 modified "2023-10-16" @default.
- W3175248253 title "PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network" @default.
- W3175248253 doi "https://doi.org/10.48550/arxiv.2104.05458" @default.
- W3175248253 hasPublicationYear "2021" @default.
- W3175248253 type Work @default.
- W3175248253 sameAs 3175248253 @default.
- W3175248253 citedByCount "2" @default.
- W3175248253 countsByYear W31752482532021 @default.
- W3175248253 crossrefType "posted-content" @default.
- W3175248253 hasAuthorship W3175248253A5016467601 @default.
- W3175248253 hasAuthorship W3175248253A5022200044 @default.
- W3175248253 hasAuthorship W3175248253A5027156714 @default.
- W3175248253 hasAuthorship W3175248253A5050031109 @default.
- W3175248253 hasAuthorship W3175248253A5051125527 @default.
- W3175248253 hasAuthorship W3175248253A5062071376 @default.
- W3175248253 hasAuthorship W3175248253A5076375120 @default.
- W3175248253 hasAuthorship W3175248253A5076936566 @default.
- W3175248253 hasAuthorship W3175248253A5079904889 @default.
- W3175248253 hasAuthorship W3175248253A5080777665 @default.
- W3175248253 hasBestOaLocation W31752482531 @default.
- W3175248253 hasConcept C119857082 @default.
- W3175248253 hasConcept C132525143 @default.
- W3175248253 hasConcept C154945302 @default.
- W3175248253 hasConcept C17744445 @default.
- W3175248253 hasConcept C199539241 @default.
- W3175248253 hasConcept C204321447 @default.
- W3175248253 hasConcept C2524010 @default.
- W3175248253 hasConcept C2779506182 @default.
- W3175248253 hasConcept C2780861071 @default.
- W3175248253 hasConcept C28719098 @default.
- W3175248253 hasConcept C33923547 @default.
- W3175248253 hasConcept C41008148 @default.
- W3175248253 hasConcept C554936623 @default.
- W3175248253 hasConcept C774472 @default.
- W3175248253 hasConcept C80444323 @default.
- W3175248253 hasConceptScore W3175248253C119857082 @default.
- W3175248253 hasConceptScore W3175248253C132525143 @default.
- W3175248253 hasConceptScore W3175248253C154945302 @default.
- W3175248253 hasConceptScore W3175248253C17744445 @default.
- W3175248253 hasConceptScore W3175248253C199539241 @default.
- W3175248253 hasConceptScore W3175248253C204321447 @default.
- W3175248253 hasConceptScore W3175248253C2524010 @default.
- W3175248253 hasConceptScore W3175248253C2779506182 @default.
- W3175248253 hasConceptScore W3175248253C2780861071 @default.
- W3175248253 hasConceptScore W3175248253C28719098 @default.
- W3175248253 hasConceptScore W3175248253C33923547 @default.
- W3175248253 hasConceptScore W3175248253C41008148 @default.
- W3175248253 hasConceptScore W3175248253C554936623 @default.
- W3175248253 hasConceptScore W3175248253C774472 @default.
- W3175248253 hasConceptScore W3175248253C80444323 @default.
- W3175248253 hasLocation W31752482531 @default.
- W3175248253 hasOpenAccess W3175248253 @default.
- W3175248253 hasPrimaryLocation W31752482531 @default.
- W3175248253 hasRelatedWork W2015373230 @default.
- W3175248253 hasRelatedWork W2034932045 @default.
- W3175248253 hasRelatedWork W2151447942 @default.
- W3175248253 hasRelatedWork W2156234372 @default.
- W3175248253 hasRelatedWork W2333817811 @default.
- W3175248253 hasRelatedWork W2334332995 @default.
- W3175248253 hasRelatedWork W2365001562 @default.
- W3175248253 hasRelatedWork W2369049097 @default.
- W3175248253 hasRelatedWork W2611614995 @default.
- W3175248253 hasRelatedWork W3107474891 @default.
- W3175248253 isParatext "false" @default.
- W3175248253 isRetracted "false" @default.
- W3175248253 magId "3175248253" @default.
- W3175248253 workType "article" @default.