Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285279070> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4285279070 endingPage "64301" @default.
- W4285279070 startingPage "64292" @default.
- W4285279070 abstract "As flowchart images become diverse and complex, existing flowchart recognition methods no longer achieve satisfactory recognition accuracy, particularly for images that contain rarely used symbols and texture backgrounds. Existing deep-learning-based object detectors and line segment detectors are promising in recognizing symbols and connecting edges separately. However, using two separate detectors for symbol and edge detection will inevitably cause unnecessary training and inference costs. Moreover, the insufficient volume and diversity of available dataset further limit the overall recognition accuracy. To address these issues, this paper proposes an end-to-end multi-task network FR-DETR (Flowchart Recognition DETection TRansformer) and a new dataset for precise and robust flowchart recognition. FR-DETR comprises a CNN backbone and a shared multi-scale Transformer structure with two prediction heads for symbol detection and edge detection respectively. The multi-scale Transformer encodes and decodes feature maps with different resolutions to jointly detect symbols and edges in a coarse-to-fine refinement process. The coarse stage uses features with low resolution and suggests candidate regions that contain potential targets for the fine stage to produce accurate predictions using features with high resolution. At each stage, every task detects targets using shared features and its respective prediction head. A new dataset is constructed to provide more symbol types and complex backgrounds for network training and evaluation. It contains more than 1000 machine-generated flowchart images, 25K+ symbol instances with nine categories, and 20K+ line segments. The experiments show that FR-DETR achieves an overall precision and recall of 94.0% and 93.1% on the proposed dataset, and 98.7% and 98.1% on the CLEF-IP dataset, respectively, which all outperform the prior methods." @default.
- W4285279070 created "2022-07-14" @default.
- W4285279070 creator A5004852618 @default.
- W4285279070 creator A5013401457 @default.
- W4285279070 creator A5085608161 @default.
- W4285279070 date "2022-01-01" @default.
- W4285279070 modified "2023-10-16" @default.
- W4285279070 title "FR-DETR: End-to-End Flowchart Recognition With Precision and Robustness" @default.
- W4285279070 cites W1536680647 @default.
- W4285279070 cites W1558424526 @default.
- W4285279070 cites W1983165733 @default.
- W4285279070 cites W1990649208 @default.
- W4285279070 cites W1995845769 @default.
- W4285279070 cites W2019894607 @default.
- W4285279070 cites W2049221653 @default.
- W4285279070 cites W2194775991 @default.
- W4285279070 cites W2798420800 @default.
- W4285279070 cites W2798943056 @default.
- W4285279070 cites W2900525909 @default.
- W4285279070 cites W2955186028 @default.
- W4285279070 cites W2981415272 @default.
- W4285279070 cites W2983785163 @default.
- W4285279070 cites W2997408160 @default.
- W4285279070 cites W2998152504 @default.
- W4285279070 cites W3085046840 @default.
- W4285279070 cites W3096609285 @default.
- W4285279070 cites W3097571420 @default.
- W4285279070 cites W3105388824 @default.
- W4285279070 cites W3143320354 @default.
- W4285279070 cites W3186564193 @default.
- W4285279070 cites W4213019189 @default.
- W4285279070 cites W639708223 @default.
- W4285279070 doi "https://doi.org/10.1109/access.2022.3183068" @default.
- W4285279070 hasPublicationYear "2022" @default.
- W4285279070 type Work @default.
- W4285279070 citedByCount "3" @default.
- W4285279070 countsByYear W42852790702023 @default.
- W4285279070 crossrefType "journal-article" @default.
- W4285279070 hasAuthorship W4285279070A5004852618 @default.
- W4285279070 hasAuthorship W4285279070A5013401457 @default.
- W4285279070 hasAuthorship W4285279070A5085608161 @default.
- W4285279070 hasBestOaLocation W42852790701 @default.
- W4285279070 hasConcept C104317684 @default.
- W4285279070 hasConcept C124101348 @default.
- W4285279070 hasConcept C153180895 @default.
- W4285279070 hasConcept C154945302 @default.
- W4285279070 hasConcept C185592680 @default.
- W4285279070 hasConcept C199360897 @default.
- W4285279070 hasConcept C2776214188 @default.
- W4285279070 hasConcept C31972630 @default.
- W4285279070 hasConcept C41008148 @default.
- W4285279070 hasConcept C55493867 @default.
- W4285279070 hasConcept C63479239 @default.
- W4285279070 hasConcept C72041958 @default.
- W4285279070 hasConcept C76155785 @default.
- W4285279070 hasConcept C94915269 @default.
- W4285279070 hasConceptScore W4285279070C104317684 @default.
- W4285279070 hasConceptScore W4285279070C124101348 @default.
- W4285279070 hasConceptScore W4285279070C153180895 @default.
- W4285279070 hasConceptScore W4285279070C154945302 @default.
- W4285279070 hasConceptScore W4285279070C185592680 @default.
- W4285279070 hasConceptScore W4285279070C199360897 @default.
- W4285279070 hasConceptScore W4285279070C2776214188 @default.
- W4285279070 hasConceptScore W4285279070C31972630 @default.
- W4285279070 hasConceptScore W4285279070C41008148 @default.
- W4285279070 hasConceptScore W4285279070C55493867 @default.
- W4285279070 hasConceptScore W4285279070C63479239 @default.
- W4285279070 hasConceptScore W4285279070C72041958 @default.
- W4285279070 hasConceptScore W4285279070C76155785 @default.
- W4285279070 hasConceptScore W4285279070C94915269 @default.
- W4285279070 hasLocation W42852790701 @default.
- W4285279070 hasOpenAccess W4285279070 @default.
- W4285279070 hasPrimaryLocation W42852790701 @default.
- W4285279070 hasRelatedWork W1199175235 @default.
- W4285279070 hasRelatedWork W1992202691 @default.
- W4285279070 hasRelatedWork W2054028780 @default.
- W4285279070 hasRelatedWork W2072196705 @default.
- W4285279070 hasRelatedWork W2131878319 @default.
- W4285279070 hasRelatedWork W2188108885 @default.
- W4285279070 hasRelatedWork W2323840003 @default.
- W4285279070 hasRelatedWork W2381593765 @default.
- W4285279070 hasRelatedWork W2906745059 @default.
- W4285279070 hasRelatedWork W2109215547 @default.
- W4285279070 hasVolume "10" @default.
- W4285279070 isParatext "false" @default.
- W4285279070 isRetracted "false" @default.
- W4285279070 workType "article" @default.