Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129111844> ?p ?o ?g. }
- W3129111844 endingPage "26441" @default.
- W3129111844 startingPage "26431" @default.
- W3129111844 abstract "Scene text detection is a task that detects the position of text in natural scenes. Due to the different sizes, arbitrary orientations, different colors of texts, as well as low contrast and resolution in the complex background, text detection in natural scene images is very challenging. So far, the detection results for text instances in motion blur, low-resolution images are still not satisfactory. In this paper, in order to solve the above problems, we propose an effective and robust text detection network that combines a state-of-the-art contrastive learning method SimCLR. Before being input to the feature extractor, the data is augmented in different methods, and then we calculate the similarity of the extracted corresponding feature pairs. This can significantly improve the performance of the detector in difficult conditions. We conduct a series of experiments on the public dataset ICDAR2013, ICDAR2015 and MSRA-TD500. On the ICDAR 2015 dataset, our method achieves F-measure of 0.840 and runs at 9.1 FPS at 720p resolution, demonstrating that the proposed method is effective and efficient." @default.
- W3129111844 created "2021-02-15" @default.
- W3129111844 creator A5030781794 @default.
- W3129111844 creator A5032940455 @default.
- W3129111844 creator A5034857130 @default.
- W3129111844 creator A5044309490 @default.
- W3129111844 creator A5045109423 @default.
- W3129111844 creator A5049396071 @default.
- W3129111844 creator A5067573420 @default.
- W3129111844 date "2021-01-01" @default.
- W3129111844 modified "2023-10-04" @default.
- W3129111844 title "A Robust and Effective Text Detector Supervised by Contrastive Learning" @default.
- W3129111844 cites W1903029394 @default.
- W3129111844 cites W1922126009 @default.
- W3129111844 cites W1978729128 @default.
- W3129111844 cites W1988461287 @default.
- W3129111844 cites W2006653496 @default.
- W3129111844 cites W2008806374 @default.
- W3129111844 cites W2009854331 @default.
- W3129111844 cites W2019478948 @default.
- W3129111844 cites W2047695704 @default.
- W3129111844 cites W2049951199 @default.
- W3129111844 cites W2061802763 @default.
- W3129111844 cites W2076014259 @default.
- W3129111844 cites W2108598243 @default.
- W3129111844 cites W2128854450 @default.
- W3129111844 cites W2131163834 @default.
- W3129111844 cites W2135231474 @default.
- W3129111844 cites W2142159465 @default.
- W3129111844 cites W2144554289 @default.
- W3129111844 cites W2165401735 @default.
- W3129111844 cites W2194187530 @default.
- W3129111844 cites W2343052201 @default.
- W3129111844 cites W2604243686 @default.
- W3129111844 cites W2604735854 @default.
- W3129111844 cites W2605076167 @default.
- W3129111844 cites W2605982830 @default.
- W3129111844 cites W2784050770 @default.
- W3129111844 cites W2962681479 @default.
- W3129111844 cites W2962804639 @default.
- W3129111844 cites W2963037989 @default.
- W3129111844 cites W2963517393 @default.
- W3129111844 cites W2963977642 @default.
- W3129111844 cites W2991626090 @default.
- W3129111844 cites W3034105996 @default.
- W3129111844 cites W3035524453 @default.
- W3129111844 cites W3038754604 @default.
- W3129111844 cites W3098090606 @default.
- W3129111844 cites W3106228955 @default.
- W3129111844 cites W654550266 @default.
- W3129111844 cites W97978472 @default.
- W3129111844 doi "https://doi.org/10.1109/access.2021.3057108" @default.
- W3129111844 hasPublicationYear "2021" @default.
- W3129111844 type Work @default.
- W3129111844 sameAs 3129111844 @default.
- W3129111844 citedByCount "3" @default.
- W3129111844 countsByYear W31291118442021 @default.
- W3129111844 countsByYear W31291118442022 @default.
- W3129111844 crossrefType "journal-article" @default.
- W3129111844 hasAuthorship W3129111844A5030781794 @default.
- W3129111844 hasAuthorship W3129111844A5032940455 @default.
- W3129111844 hasAuthorship W3129111844A5034857130 @default.
- W3129111844 hasAuthorship W3129111844A5044309490 @default.
- W3129111844 hasAuthorship W3129111844A5045109423 @default.
- W3129111844 hasAuthorship W3129111844A5049396071 @default.
- W3129111844 hasAuthorship W3129111844A5067573420 @default.
- W3129111844 hasBestOaLocation W31291118441 @default.
- W3129111844 hasConcept C103278499 @default.
- W3129111844 hasConcept C115961682 @default.
- W3129111844 hasConcept C117978034 @default.
- W3129111844 hasConcept C127413603 @default.
- W3129111844 hasConcept C138885662 @default.
- W3129111844 hasConcept C153180895 @default.
- W3129111844 hasConcept C154945302 @default.
- W3129111844 hasConcept C21880701 @default.
- W3129111844 hasConcept C2776401178 @default.
- W3129111844 hasConcept C2776502983 @default.
- W3129111844 hasConcept C2777708103 @default.
- W3129111844 hasConcept C2983589003 @default.
- W3129111844 hasConcept C31972630 @default.
- W3129111844 hasConcept C41008148 @default.
- W3129111844 hasConcept C41895202 @default.
- W3129111844 hasConcept C52622490 @default.
- W3129111844 hasConcept C76155785 @default.
- W3129111844 hasConcept C94915269 @default.
- W3129111844 hasConceptScore W3129111844C103278499 @default.
- W3129111844 hasConceptScore W3129111844C115961682 @default.
- W3129111844 hasConceptScore W3129111844C117978034 @default.
- W3129111844 hasConceptScore W3129111844C127413603 @default.
- W3129111844 hasConceptScore W3129111844C138885662 @default.
- W3129111844 hasConceptScore W3129111844C153180895 @default.
- W3129111844 hasConceptScore W3129111844C154945302 @default.
- W3129111844 hasConceptScore W3129111844C21880701 @default.
- W3129111844 hasConceptScore W3129111844C2776401178 @default.
- W3129111844 hasConceptScore W3129111844C2776502983 @default.
- W3129111844 hasConceptScore W3129111844C2777708103 @default.
- W3129111844 hasConceptScore W3129111844C2983589003 @default.
- W3129111844 hasConceptScore W3129111844C31972630 @default.