Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022980286> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W3022980286 abstract "Word Spotting of Historical Arabic Documents is a challenging task due to the complexity of document layouts. This paper proposes a novel word spotting approach that consists of learning feature representation to describe word images. The objective is to investigate optimal embedding spaces to extract a discriminative word image representation. The proposed approach consists of two steps: i) construct a CNN-based embedding space with triplet-loss and then ii) match embedding representations using the Euclidean distance. For training, the CNN takes as input a set of triplet samples (anchor, positive sample and negative sample). Then, the triplet loss serves to create a novel space by minimizing intra-classes distances and maximizing inter-classes distances. The proposed approach is evaluated on the VML-HD dataset and the experiments show its effectiveness compared to the state of the art." @default.
- W3022980286 created "2020-05-13" @default.
- W3022980286 creator A5030346646 @default.
- W3022980286 creator A5049108338 @default.
- W3022980286 creator A5050118866 @default.
- W3022980286 creator A5050773373 @default.
- W3022980286 date "2019-12-12" @default.
- W3022980286 modified "2023-10-18" @default.
- W3022980286 title "Triplet CNN-based word spotting of historical Arabic documents" @default.
- W3022980286 cites W1928278792 @default.
- W3022980286 cites W1964653201 @default.
- W3022980286 cites W2095962836 @default.
- W3022980286 cites W2740745994 @default.
- W3022980286 hasPublicationYear "2019" @default.
- W3022980286 type Work @default.
- W3022980286 sameAs 3022980286 @default.
- W3022980286 citedByCount "1" @default.
- W3022980286 countsByYear W30229802862020 @default.
- W3022980286 crossrefType "proceedings-article" @default.
- W3022980286 hasAuthorship W3022980286A5030346646 @default.
- W3022980286 hasAuthorship W3022980286A5049108338 @default.
- W3022980286 hasAuthorship W3022980286A5050118866 @default.
- W3022980286 hasAuthorship W3022980286A5050773373 @default.
- W3022980286 hasConcept C138885662 @default.
- W3022980286 hasConcept C154945302 @default.
- W3022980286 hasConcept C204321447 @default.
- W3022980286 hasConcept C2779506182 @default.
- W3022980286 hasConcept C2781213101 @default.
- W3022980286 hasConcept C41008148 @default.
- W3022980286 hasConcept C41895202 @default.
- W3022980286 hasConcept C90805587 @default.
- W3022980286 hasConcept C96455323 @default.
- W3022980286 hasConceptScore W3022980286C138885662 @default.
- W3022980286 hasConceptScore W3022980286C154945302 @default.
- W3022980286 hasConceptScore W3022980286C204321447 @default.
- W3022980286 hasConceptScore W3022980286C2779506182 @default.
- W3022980286 hasConceptScore W3022980286C2781213101 @default.
- W3022980286 hasConceptScore W3022980286C41008148 @default.
- W3022980286 hasConceptScore W3022980286C41895202 @default.
- W3022980286 hasConceptScore W3022980286C90805587 @default.
- W3022980286 hasConceptScore W3022980286C96455323 @default.
- W3022980286 hasLocation W30229802861 @default.
- W3022980286 hasLocation W30229802862 @default.
- W3022980286 hasOpenAccess W3022980286 @default.
- W3022980286 hasPrimaryLocation W30229802861 @default.
- W3022980286 hasRelatedWork W1554833030 @default.
- W3022980286 hasRelatedWork W2137084580 @default.
- W3022980286 hasRelatedWork W2323788589 @default.
- W3022980286 hasRelatedWork W2335190990 @default.
- W3022980286 hasRelatedWork W2530078870 @default.
- W3022980286 hasRelatedWork W2742860341 @default.
- W3022980286 hasRelatedWork W2993452628 @default.
- W3022980286 hasRelatedWork W3018114492 @default.
- W3022980286 hasRelatedWork W3049223976 @default.
- W3022980286 hasRelatedWork W4248007934 @default.
- W3022980286 isParatext "false" @default.
- W3022980286 isRetracted "false" @default.
- W3022980286 magId "3022980286" @default.
- W3022980286 workType "article" @default.