Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211151565> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3211151565 abstract "Affinity graph-based segmentation methods have become a major trend in computer vision. The performance of these methods relies on the constructed affinity graph, with particular emphasis on the neighborhood topology and pairwise affinities among superpixels. Due to the advantages of assimilating different graphs, a multi-scale fusion graph has a better performance than a single graph with single-scale. However, these methods ignore the noise from images which influences the accuracy of pairwise similarities. Multi-scale combinatorial grouping and graph fusion also generate a higher computational complexity. In this paper, we propose an adaptive fusion affinity graph (AFA-graph) with noise-free low-rank representation in an online manner for natural image segmentation. An input image is first over-segmented into superpixels at different scales and then filtered by the proposed improved kernel density estimation method. Moreover, we select global nodes of these superpixels on the basis of their subspace-preserving presentation, which reveals the feature distribution of superpixels exactly. To reduce time complexity while improving performance, a sparse representation of global nodes based on noise-free online low-rank representation is used to obtain a global graph at each scale. The global graph is finally used to update a local graph which is built upon all superpixels at each scale. Experimental results on the BSD300, BSD500, MSRC, SBD, and PASCAL VOC show the effectiveness of AFA-graph in comparison with state-of-the-art approaches." @default.
- W3211151565 created "2021-11-08" @default.
- W3211151565 creator A5004407603 @default.
- W3211151565 creator A5016553220 @default.
- W3211151565 creator A5027899074 @default.
- W3211151565 creator A5070302048 @default.
- W3211151565 creator A5071335561 @default.
- W3211151565 date "2021-10-22" @default.
- W3211151565 modified "2023-09-26" @default.
- W3211151565 title "Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation" @default.
- W3211151565 cites W1498238238 @default.
- W3211151565 cites W1528789833 @default.
- W3211151565 cites W1591116419 @default.
- W3211151565 cites W1808966389 @default.
- W3211151565 cites W1973771202 @default.
- W3211151565 cites W1993962865 @default.
- W3211151565 cites W1997201895 @default.
- W3211151565 cites W1999478155 @default.
- W3211151565 cites W2009685382 @default.
- W3211151565 cites W2010975286 @default.
- W3211151565 cites W2014795190 @default.
- W3211151565 cites W2031489346 @default.
- W3211151565 cites W2067191022 @default.
- W3211151565 cites W2078056852 @default.
- W3211151565 cites W2097323414 @default.
- W3211151565 cites W2102706263 @default.
- W3211151565 cites W2116373927 @default.
- W3211151565 cites W2121189958 @default.
- W3211151565 cites W2121927366 @default.
- W3211151565 cites W2121947440 @default.
- W3211151565 cites W2130838651 @default.
- W3211151565 cites W2154992274 @default.
- W3211151565 cites W2157305458 @default.
- W3211151565 cites W2165232124 @default.
- W3211151565 cites W2165423399 @default.
- W3211151565 cites W2214925677 @default.
- W3211151565 cites W2404771443 @default.
- W3211151565 cites W2412026543 @default.
- W3211151565 cites W2472530926 @default.
- W3211151565 cites W2536208356 @default.
- W3211151565 cites W2766692216 @default.
- W3211151565 cites W2785177491 @default.
- W3211151565 cites W2963840432 @default.
- W3211151565 cites W2963961044 @default.
- W3211151565 cites W2965799248 @default.
- W3211151565 cites W3036790830 @default.
- W3211151565 cites W3089501380 @default.
- W3211151565 doi "https://doi.org/10.48550/arxiv.2110.11685" @default.
- W3211151565 hasPublicationYear "2021" @default.
- W3211151565 type Work @default.
- W3211151565 sameAs 3211151565 @default.
- W3211151565 citedByCount "0" @default.
- W3211151565 crossrefType "posted-content" @default.
- W3211151565 hasAuthorship W3211151565A5004407603 @default.
- W3211151565 hasAuthorship W3211151565A5016553220 @default.
- W3211151565 hasAuthorship W3211151565A5027899074 @default.
- W3211151565 hasAuthorship W3211151565A5070302048 @default.
- W3211151565 hasAuthorship W3211151565A5071335561 @default.
- W3211151565 hasBestOaLocation W32111515651 @default.
- W3211151565 hasConcept C132525143 @default.
- W3211151565 hasConcept C153180895 @default.
- W3211151565 hasConcept C154945302 @default.
- W3211151565 hasConcept C184898388 @default.
- W3211151565 hasConcept C199360897 @default.
- W3211151565 hasConcept C32834561 @default.
- W3211151565 hasConcept C33923547 @default.
- W3211151565 hasConcept C41008148 @default.
- W3211151565 hasConcept C75608658 @default.
- W3211151565 hasConcept C80444323 @default.
- W3211151565 hasConcept C89600930 @default.
- W3211151565 hasConceptScore W3211151565C132525143 @default.
- W3211151565 hasConceptScore W3211151565C153180895 @default.
- W3211151565 hasConceptScore W3211151565C154945302 @default.
- W3211151565 hasConceptScore W3211151565C184898388 @default.
- W3211151565 hasConceptScore W3211151565C199360897 @default.
- W3211151565 hasConceptScore W3211151565C32834561 @default.
- W3211151565 hasConceptScore W3211151565C33923547 @default.
- W3211151565 hasConceptScore W3211151565C41008148 @default.
- W3211151565 hasConceptScore W3211151565C75608658 @default.
- W3211151565 hasConceptScore W3211151565C80444323 @default.
- W3211151565 hasConceptScore W3211151565C89600930 @default.
- W3211151565 hasLocation W32111515651 @default.
- W3211151565 hasOpenAccess W3211151565 @default.
- W3211151565 hasPrimaryLocation W32111515651 @default.
- W3211151565 hasRelatedWork W2016349419 @default.
- W3211151565 hasRelatedWork W2042327336 @default.
- W3211151565 hasRelatedWork W2294652642 @default.
- W3211151565 hasRelatedWork W2510758617 @default.
- W3211151565 hasRelatedWork W2543161807 @default.
- W3211151565 hasRelatedWork W2799124825 @default.
- W3211151565 hasRelatedWork W2897195263 @default.
- W3211151565 hasRelatedWork W3161467835 @default.
- W3211151565 hasRelatedWork W4206076898 @default.
- W3211151565 hasRelatedWork W4226401448 @default.
- W3211151565 isParatext "false" @default.
- W3211151565 isRetracted "false" @default.
- W3211151565 magId "3211151565" @default.
- W3211151565 workType "article" @default.