Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176268775> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3176268775 endingPage "2933" @default.
- W3176268775 startingPage "2925" @default.
- W3176268775 abstract "Recent handwritten mathematical expression recognition (HMER) approaches treat the problem as an image-to-markup generation task where the handwritten formula is translated into a sequence (e.g. LaTeX). The encoder-decoder framework is widely used to solve this image-to-sequence problem. However, (i) for structured mathematical formula, the hierarchical structure neither in the formula nor in the markup has been explored adequately. In addition, (ii) existing image-to-markup methods could not explicitly segment mathematical symbols in the formula corresponding to each target markup token. In this paper, we address the above issues by formulating the HMER as a graph-to-graph (G2G) learning problem. Graph is more flexible and general for structure representation and learning compared with image or sequence. At the core of our method lies the embedding of input formula and output markup into graphs on primitives, with Graph Neural Networks (GNN) to explore the structural information, and a novel sub-graph attention mechanism to match primitives in the input and output graphs. We conduct extensive experiments on CROHME datasets to demonstrate the benefits of the proposed G2G model. Our method yields significant improvements over previous SOTA image-to-markup systems. Moreover, it explicitly resolves the symbol segmentation problem while still being trained end-to-end, making the whole system much more accurate and interpretable." @default.
- W3176268775 created "2021-07-05" @default.
- W3176268775 creator A5019724982 @default.
- W3176268775 creator A5039310938 @default.
- W3176268775 creator A5042530503 @default.
- W3176268775 creator A5056296476 @default.
- W3176268775 creator A5082548671 @default.
- W3176268775 date "2021-05-18" @default.
- W3176268775 modified "2023-10-16" @default.
- W3176268775 title "Graph-to-Graph: Towards Accurate and Interpretable Online Handwritten Mathematical Expression Recognition" @default.
- W3176268775 cites W1514535095 @default.
- W3176268775 cites W1810641085 @default.
- W3176268775 cites W1978799108 @default.
- W3176268775 cites W2031071334 @default.
- W3176268775 cites W2072449446 @default.
- W3176268775 cites W2153971293 @default.
- W3176268775 cites W2528252828 @default.
- W3176268775 cites W2575842049 @default.
- W3176268775 cites W2576123216 @default.
- W3176268775 cites W2604729005 @default.
- W3176268775 cites W2623860192 @default.
- W3176268775 cites W2785656387 @default.
- W3176268775 cites W2806717845 @default.
- W3176268775 cites W2890531016 @default.
- W3176268775 cites W2905413777 @default.
- W3176268775 cites W2922714365 @default.
- W3176268775 cites W2963311793 @default.
- W3176268775 cites W2963637207 @default.
- W3176268775 cites W2963858333 @default.
- W3176268775 cites W2963970792 @default.
- W3176268775 cites W2964121744 @default.
- W3176268775 cites W2964265128 @default.
- W3176268775 cites W2964308564 @default.
- W3176268775 cites W2997386764 @default.
- W3176268775 cites W3002575754 @default.
- W3176268775 cites W3003410955 @default.
- W3176268775 cites W3004194266 @default.
- W3176268775 cites W3034537864 @default.
- W3176268775 cites W3034799230 @default.
- W3176268775 cites W3035481209 @default.
- W3176268775 cites W854541894 @default.
- W3176268775 doi "https://doi.org/10.1609/aaai.v35i4.16399" @default.
- W3176268775 hasPublicationYear "2021" @default.
- W3176268775 type Work @default.
- W3176268775 sameAs 3176268775 @default.
- W3176268775 citedByCount "13" @default.
- W3176268775 countsByYear W31762687752021 @default.
- W3176268775 countsByYear W31762687752022 @default.
- W3176268775 countsByYear W31762687752023 @default.
- W3176268775 crossrefType "journal-article" @default.
- W3176268775 hasAuthorship W3176268775A5019724982 @default.
- W3176268775 hasAuthorship W3176268775A5039310938 @default.
- W3176268775 hasAuthorship W3176268775A5042530503 @default.
- W3176268775 hasAuthorship W3176268775A5056296476 @default.
- W3176268775 hasAuthorship W3176268775A5082548671 @default.
- W3176268775 hasBestOaLocation W31762687751 @default.
- W3176268775 hasConcept C111919701 @default.
- W3176268775 hasConcept C11413529 @default.
- W3176268775 hasConcept C118505674 @default.
- W3176268775 hasConcept C132525143 @default.
- W3176268775 hasConcept C153180895 @default.
- W3176268775 hasConcept C154945302 @default.
- W3176268775 hasConcept C41008148 @default.
- W3176268775 hasConcept C41608201 @default.
- W3176268775 hasConcept C45874996 @default.
- W3176268775 hasConcept C80444323 @default.
- W3176268775 hasConcept C8797682 @default.
- W3176268775 hasConceptScore W3176268775C111919701 @default.
- W3176268775 hasConceptScore W3176268775C11413529 @default.
- W3176268775 hasConceptScore W3176268775C118505674 @default.
- W3176268775 hasConceptScore W3176268775C132525143 @default.
- W3176268775 hasConceptScore W3176268775C153180895 @default.
- W3176268775 hasConceptScore W3176268775C154945302 @default.
- W3176268775 hasConceptScore W3176268775C41008148 @default.
- W3176268775 hasConceptScore W3176268775C41608201 @default.
- W3176268775 hasConceptScore W3176268775C45874996 @default.
- W3176268775 hasConceptScore W3176268775C80444323 @default.
- W3176268775 hasConceptScore W3176268775C8797682 @default.
- W3176268775 hasIssue "4" @default.
- W3176268775 hasLocation W31762687751 @default.
- W3176268775 hasOpenAccess W3176268775 @default.
- W3176268775 hasPrimaryLocation W31762687751 @default.
- W3176268775 hasRelatedWork W1486692450 @default.
- W3176268775 hasRelatedWork W1566913699 @default.
- W3176268775 hasRelatedWork W1889092586 @default.
- W3176268775 hasRelatedWork W2081328318 @default.
- W3176268775 hasRelatedWork W2127574606 @default.
- W3176268775 hasRelatedWork W2932872266 @default.
- W3176268775 hasRelatedWork W2954418080 @default.
- W3176268775 hasRelatedWork W3121570353 @default.
- W3176268775 hasRelatedWork W4385386698 @default.
- W3176268775 hasRelatedWork W818235636 @default.
- W3176268775 hasVolume "35" @default.
- W3176268775 isParatext "false" @default.
- W3176268775 isRetracted "false" @default.
- W3176268775 magId "3176268775" @default.
- W3176268775 workType "article" @default.