FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386008071> ?p ?o ?g. }

• W4386008071 endingPage "325" @default.
• W4386008071 startingPage "307" @default.
• W4386008071 abstract "Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a unified transformer encoder-decoder architecture for en-to-end instance segmentation of complex layouts in document images. The method adapts a contrastive training with a mixed query selection for anchor initialization in the decoder. Later on, it performs a dot product between the obtained query embeddings and the pixel embedding map (coming from the encoder) for semantic reasoning. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ), and TableBank demonstrate that our model with SwinL backbone achieves better segmentation performance than the existing state-of-the-art approaches with the average precision of 93.72, 54.39, 84.65 and 98.04 respectively under one billion parameters. The code is made publicly available at: github.com/ayanban011/SwinDocSegmenter ." @default.
• W4386008071 created "2023-08-20" @default.
• W4386008071 creator A5015845388 @default.
• W4386008071 creator A5060424729 @default.
• W4386008071 creator A5065907624 @default.
• W4386008071 creator A5068803496 @default.
• W4386008071 date "2023-01-01" @default.
• W4386008071 modified "2023-10-14" @default.
• W4386008071 title "SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation" @default.
• W4386008071 cites W1861492603 @default.
• W4386008071 cites W1981453410 @default.
• W4386008071 cites W2001908502 @default.
• W4386008071 cites W2028530780 @default.
• W4386008071 cites W2055408294 @default.
• W4386008071 cites W2097323614 @default.
• W4386008071 cites W2126925189 @default.
• W4386008071 cites W2156839780 @default.
• W4386008071 cites W2565639579 @default.
• W4386008071 cites W2786162033 @default.
• W4386008071 cites W2787835872 @default.
• W4386008071 cites W2962772269 @default.
• W4386008071 cites W2962903028 @default.
• W4386008071 cites W2970987838 @default.
• W4386008071 cites W3003334191 @default.
• W4386008071 cites W3003711898 @default.
• W4386008071 cites W3004040469 @default.
• W4386008071 cites W3004186774 @default.
• W4386008071 cites W3008567343 @default.
• W4386008071 cites W3034404784 @default.
• W4386008071 cites W3034997246 @default.
• W4386008071 cites W3035011051 @default.
• W4386008071 cites W3049292294 @default.
• W4386008071 cites W3138516171 @default.
• W4386008071 cites W3163476226 @default.
• W4386008071 cites W3176664887 @default.
• W4386008071 cites W3194824089 @default.
• W4386008071 cites W3202466114 @default.
• W4386008071 cites W3202839357 @default.
• W4386008071 cites W3205981739 @default.
• W4386008071 cites W3207026744 @default.
• W4386008071 cites W4221167941 @default.
• W4386008071 cites W4290927927 @default.
• W4386008071 cites W4304013646 @default.
• W4386008071 cites W4304014014 @default.
• W4386008071 cites W4308236023 @default.
• W4386008071 cites W4312233877 @default.
• W4386008071 cites W4312960790 @default.
• W4386008071 cites W4319300221 @default.
• W4386008071 cites W4319301060 @default.
• W4386008071 doi "https://doi.org/10.1007/978-3-031-41676-7_18" @default.
• W4386008071 hasPublicationYear "2023" @default.
• W4386008071 type Work @default.
• W4386008071 citedByCount "0" @default.
• W4386008071 crossrefType "book-chapter" @default.
• W4386008071 hasAuthorship W4386008071A5015845388 @default.
• W4386008071 hasAuthorship W4386008071A5060424729 @default.
• W4386008071 hasAuthorship W4386008071A5065907624 @default.
• W4386008071 hasAuthorship W4386008071A5068803496 @default.
• W4386008071 hasBestOaLocation W43860080712 @default.
• W4386008071 hasConcept C111919701 @default.
• W4386008071 hasConcept C114466953 @default.
• W4386008071 hasConcept C118505674 @default.
• W4386008071 hasConcept C121332964 @default.
• W4386008071 hasConcept C124504099 @default.
• W4386008071 hasConcept C137293760 @default.
• W4386008071 hasConcept C153180895 @default.
• W4386008071 hasConcept C154945302 @default.
• W4386008071 hasConcept C160633673 @default.
• W4386008071 hasConcept C165801399 @default.
• W4386008071 hasConcept C186644900 @default.
• W4386008071 hasConcept C199360897 @default.
• W4386008071 hasConcept C23123220 @default.
• W4386008071 hasConcept C2778371909 @default.
• W4386008071 hasConcept C31972630 @default.
• W4386008071 hasConcept C41008148 @default.
• W4386008071 hasConcept C41608201 @default.
• W4386008071 hasConcept C62520636 @default.
• W4386008071 hasConcept C66322947 @default.
• W4386008071 hasConcept C89600930 @default.
• W4386008071 hasConceptScore W4386008071C111919701 @default.
• W4386008071 hasConceptScore W4386008071C114466953 @default.
• W4386008071 hasConceptScore W4386008071C118505674 @default.
• W4386008071 hasConceptScore W4386008071C121332964 @default.
• W4386008071 hasConceptScore W4386008071C124504099 @default.
• W4386008071 hasConceptScore W4386008071C137293760 @default.
• W4386008071 hasConceptScore W4386008071C153180895 @default.
• W4386008071 hasConceptScore W4386008071C154945302 @default.
• W4386008071 hasConceptScore W4386008071C160633673 @default.
• W4386008071 hasConceptScore W4386008071C165801399 @default.
• W4386008071 hasConceptScore W4386008071C186644900 @default.
• W4386008071 hasConceptScore W4386008071C199360897 @default.
• W4386008071 hasConceptScore W4386008071C23123220 @default.
• W4386008071 hasConceptScore W4386008071C2778371909 @default.
• W4386008071 hasConceptScore W4386008071C31972630 @default.
• W4386008071 hasConceptScore W4386008071C41008148 @default.
• W4386008071 hasConceptScore W4386008071C41608201 @default.
• W4386008071 hasConceptScore W4386008071C62520636 @default.
• W4386008071 hasConceptScore W4386008071C66322947 @default.

• next