Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080326> ?p ?o ?g. }
- W4304080326 abstract "In this paper, we present a simple yet efficient framework, BlumNet, for extracting object skeletons in natural images and binary shapes. With the need for highly reliable skeletons in various multimedia applications, the proposed BlumNet is distinguished in three aspects: (1) The inception of graph decomposition and reconstruction strategies further simplifies the skeleton extraction task into a graph component detection problem, which significantly improves the accuracy and robustness of extracted skeletons. (2) The intuitive representation of each skeleton branch with multiple structured and overlapping line segments can effectively prevent the skeleton branch vanishing problem. (3) In comparison to traditional skeleton heatmaps, our approach directly outputs skeleton graphs, which is more feasible for real-world applications. Through comprehensive experiments, we demonstrate the advantages of BlumNet: significantly higher accuracy than the state-of-the-art AdaLSN (0.826 vs. 0.786) on the SK1491 dataset, a marked improvement in robustness on mixed object deformations, and also a state-of-the-art performance on binary shape datasets (e.g. 0.893 on the MPEG7 dataset)." @default.
- W4304080326 created "2022-10-10" @default.
- W4304080326 creator A5011213742 @default.
- W4304080326 creator A5037990310 @default.
- W4304080326 creator A5076753547 @default.
- W4304080326 creator A5083662293 @default.
- W4304080326 creator A5090586726 @default.
- W4304080326 date "2022-10-10" @default.
- W4304080326 modified "2023-10-16" @default.
- W4304080326 title "BlumNet: Graph Component Detection for Object Skeleton Extraction" @default.
- W4304080326 cites W1495971627 @default.
- W4304080326 cites W174734558 @default.
- W4304080326 cites W1901129140 @default.
- W4304080326 cites W1935817682 @default.
- W4304080326 cites W1973312669 @default.
- W4304080326 cites W1994472027 @default.
- W4304080326 cites W2007485653 @default.
- W4304080326 cites W2024335283 @default.
- W4304080326 cites W2039367092 @default.
- W4304080326 cites W2052516389 @default.
- W4304080326 cites W2099673295 @default.
- W4304080326 cites W2104093257 @default.
- W4304080326 cites W2111569598 @default.
- W4304080326 cites W2114766304 @default.
- W4304080326 cites W2116663904 @default.
- W4304080326 cites W2130072711 @default.
- W4304080326 cites W2133814640 @default.
- W4304080326 cites W2160306297 @default.
- W4304080326 cites W2164102350 @default.
- W4304080326 cites W2222512263 @default.
- W4304080326 cites W2263462986 @default.
- W4304080326 cites W2517954747 @default.
- W4304080326 cites W2518902831 @default.
- W4304080326 cites W2584558395 @default.
- W4304080326 cites W2591692311 @default.
- W4304080326 cites W2604709832 @default.
- W4304080326 cites W2765819532 @default.
- W4304080326 cites W2883596444 @default.
- W4304080326 cites W2953809838 @default.
- W4304080326 cites W2955186028 @default.
- W4304080326 cites W2963722952 @default.
- W4304080326 cites W2964216471 @default.
- W4304080326 cites W2964304707 @default.
- W4304080326 cites W2979796099 @default.
- W4304080326 cites W2981415272 @default.
- W4304080326 cites W3035228270 @default.
- W4304080326 cites W3096609285 @default.
- W4304080326 cites W3108705364 @default.
- W4304080326 cites W3126271000 @default.
- W4304080326 cites W3128918010 @default.
- W4304080326 cites W3138516171 @default.
- W4304080326 cites W3145450519 @default.
- W4304080326 cites W3152977384 @default.
- W4304080326 cites W3161503361 @default.
- W4304080326 cites W3186564193 @default.
- W4304080326 cites W3200379731 @default.
- W4304080326 cites W3207725326 @default.
- W4304080326 cites W3211170313 @default.
- W4304080326 cites W845365781 @default.
- W4304080326 doi "https://doi.org/10.1145/3503161.3547816" @default.
- W4304080326 hasPublicationYear "2022" @default.
- W4304080326 type Work @default.
- W4304080326 citedByCount "3" @default.
- W4304080326 countsByYear W43040803262022 @default.
- W4304080326 countsByYear W43040803262023 @default.
- W4304080326 crossrefType "proceedings-article" @default.
- W4304080326 hasAuthorship W4304080326A5011213742 @default.
- W4304080326 hasAuthorship W4304080326A5037990310 @default.
- W4304080326 hasAuthorship W4304080326A5076753547 @default.
- W4304080326 hasAuthorship W4304080326A5083662293 @default.
- W4304080326 hasAuthorship W4304080326A5090586726 @default.
- W4304080326 hasConcept C104317684 @default.
- W4304080326 hasConcept C112785775 @default.
- W4304080326 hasConcept C129641003 @default.
- W4304080326 hasConcept C132525143 @default.
- W4304080326 hasConcept C153180895 @default.
- W4304080326 hasConcept C154945302 @default.
- W4304080326 hasConcept C185592680 @default.
- W4304080326 hasConcept C18969341 @default.
- W4304080326 hasConcept C193435613 @default.
- W4304080326 hasConcept C199360897 @default.
- W4304080326 hasConcept C31972630 @default.
- W4304080326 hasConcept C33923547 @default.
- W4304080326 hasConcept C41008148 @default.
- W4304080326 hasConcept C48372109 @default.
- W4304080326 hasConcept C55493867 @default.
- W4304080326 hasConcept C63479239 @default.
- W4304080326 hasConcept C80444323 @default.
- W4304080326 hasConcept C89600930 @default.
- W4304080326 hasConcept C94375191 @default.
- W4304080326 hasConceptScore W4304080326C104317684 @default.
- W4304080326 hasConceptScore W4304080326C112785775 @default.
- W4304080326 hasConceptScore W4304080326C129641003 @default.
- W4304080326 hasConceptScore W4304080326C132525143 @default.
- W4304080326 hasConceptScore W4304080326C153180895 @default.
- W4304080326 hasConceptScore W4304080326C154945302 @default.
- W4304080326 hasConceptScore W4304080326C185592680 @default.
- W4304080326 hasConceptScore W4304080326C18969341 @default.
- W4304080326 hasConceptScore W4304080326C193435613 @default.
- W4304080326 hasConceptScore W4304080326C199360897 @default.