Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386158757> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4386158757 abstract "Over the past few years, segmentation-based text detection methods have achieved great progress in the scene text detection field. However, most of the existing methods with FPN tend to ignore the feature misalignment issues caused by semantic gap between features at different levels, leading to inaccurate segmentation prediction. Therefore, we propose an end-to-end trainable text detector to alleviate the above dilemma. Specifically, we propose an Adaptive Feature Transform Module (AFTM) to adaptively align features of different levels. Furthermore, a Cross-Level Attention (CLA) block is developed to capture the cross-level information, and selectively enhance element-wise features of multi-level feature maps. Experiments on four benchmark datasets, MSRA-TD500, Total-Text, CTW1500 and ICDAR2015, demonstrate that our proposed method has competitive performance and strong robustness." @default.
- W4386158757 created "2023-08-26" @default.
- W4386158757 creator A5036035213 @default.
- W4386158757 creator A5048262602 @default.
- W4386158757 date "2023-07-01" @default.
- W4386158757 modified "2023-09-23" @default.
- W4386158757 title "Cross-Level Attention Based Adaptive Feature Alignment Network for Arbitrary-Shaped Text Detection" @default.
- W4386158757 cites W1988461287 @default.
- W4386158757 cites W2108598243 @default.
- W4386158757 cites W2144554289 @default.
- W4386158757 cites W2194775991 @default.
- W4386158757 cites W2343052201 @default.
- W4386158757 cites W2565639579 @default.
- W4386158757 cites W2605982830 @default.
- W4386158757 cites W2752782242 @default.
- W4386158757 cites W2963647456 @default.
- W4386158757 cites W2998621280 @default.
- W4386158757 cites W3034514377 @default.
- W4386158757 cites W3035679705 @default.
- W4386158757 cites W3106228955 @default.
- W4386158757 cites W3133630855 @default.
- W4386158757 cites W3138649552 @default.
- W4386158757 cites W3172799005 @default.
- W4386158757 cites W3181016597 @default.
- W4386158757 cites W3186906052 @default.
- W4386158757 cites W4214922754 @default.
- W4386158757 cites W639708223 @default.
- W4386158757 doi "https://doi.org/10.1109/icme55011.2023.00383" @default.
- W4386158757 hasPublicationYear "2023" @default.
- W4386158757 type Work @default.
- W4386158757 citedByCount "0" @default.
- W4386158757 crossrefType "proceedings-article" @default.
- W4386158757 hasAuthorship W4386158757A5036035213 @default.
- W4386158757 hasAuthorship W4386158757A5048262602 @default.
- W4386158757 hasConcept C104317684 @default.
- W4386158757 hasConcept C115961682 @default.
- W4386158757 hasConcept C13280743 @default.
- W4386158757 hasConcept C138885662 @default.
- W4386158757 hasConcept C153180895 @default.
- W4386158757 hasConcept C154945302 @default.
- W4386158757 hasConcept C185592680 @default.
- W4386158757 hasConcept C185798385 @default.
- W4386158757 hasConcept C205649164 @default.
- W4386158757 hasConcept C2524010 @default.
- W4386158757 hasConcept C2776151529 @default.
- W4386158757 hasConcept C2776401178 @default.
- W4386158757 hasConcept C2777210771 @default.
- W4386158757 hasConcept C2781122975 @default.
- W4386158757 hasConcept C2983589003 @default.
- W4386158757 hasConcept C33923547 @default.
- W4386158757 hasConcept C41008148 @default.
- W4386158757 hasConcept C41895202 @default.
- W4386158757 hasConcept C52622490 @default.
- W4386158757 hasConcept C55493867 @default.
- W4386158757 hasConcept C63479239 @default.
- W4386158757 hasConcept C76155785 @default.
- W4386158757 hasConcept C89600930 @default.
- W4386158757 hasConcept C94915269 @default.
- W4386158757 hasConceptScore W4386158757C104317684 @default.
- W4386158757 hasConceptScore W4386158757C115961682 @default.
- W4386158757 hasConceptScore W4386158757C13280743 @default.
- W4386158757 hasConceptScore W4386158757C138885662 @default.
- W4386158757 hasConceptScore W4386158757C153180895 @default.
- W4386158757 hasConceptScore W4386158757C154945302 @default.
- W4386158757 hasConceptScore W4386158757C185592680 @default.
- W4386158757 hasConceptScore W4386158757C185798385 @default.
- W4386158757 hasConceptScore W4386158757C205649164 @default.
- W4386158757 hasConceptScore W4386158757C2524010 @default.
- W4386158757 hasConceptScore W4386158757C2776151529 @default.
- W4386158757 hasConceptScore W4386158757C2776401178 @default.
- W4386158757 hasConceptScore W4386158757C2777210771 @default.
- W4386158757 hasConceptScore W4386158757C2781122975 @default.
- W4386158757 hasConceptScore W4386158757C2983589003 @default.
- W4386158757 hasConceptScore W4386158757C33923547 @default.
- W4386158757 hasConceptScore W4386158757C41008148 @default.
- W4386158757 hasConceptScore W4386158757C41895202 @default.
- W4386158757 hasConceptScore W4386158757C52622490 @default.
- W4386158757 hasConceptScore W4386158757C55493867 @default.
- W4386158757 hasConceptScore W4386158757C63479239 @default.
- W4386158757 hasConceptScore W4386158757C76155785 @default.
- W4386158757 hasConceptScore W4386158757C89600930 @default.
- W4386158757 hasConceptScore W4386158757C94915269 @default.
- W4386158757 hasLocation W43861587571 @default.
- W4386158757 hasOpenAccess W4386158757 @default.
- W4386158757 hasPrimaryLocation W43861587571 @default.
- W4386158757 hasRelatedWork W1964120219 @default.
- W4386158757 hasRelatedWork W2000165426 @default.
- W4386158757 hasRelatedWork W2144059113 @default.
- W4386158757 hasRelatedWork W2146076056 @default.
- W4386158757 hasRelatedWork W2385132419 @default.
- W4386158757 hasRelatedWork W2546942002 @default.
- W4386158757 hasRelatedWork W2734888972 @default.
- W4386158757 hasRelatedWork W2772780115 @default.
- W4386158757 hasRelatedWork W2811390910 @default.
- W4386158757 hasRelatedWork W3003836766 @default.
- W4386158757 isParatext "false" @default.
- W4386158757 isRetracted "false" @default.
- W4386158757 workType "article" @default.