Matches in SemOpenAlex for { <https://semopenalex.org/work/W2796972250> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2796972250 abstract "In this paper we address the problem of unsupervised localization of objects in single images. Compared to previous state-of-the-art method our method is fully unsupervised in the sense that there is no prior instance level or category level information about the image. Furthermore, we treat each image individually and do not rely on any neighboring image similarity. We employ deep-learning based generation of saliency maps and region proposals to tackle this problem. First salient regions in the image are determined using an encoder/decoder architecture. The resulting saliency map is matched with region proposals from a class agnostic region proposal network to roughly localize the candidate object regions. These regions are further refined based on the overlap and similarity ratios. Our experimental evaluations on a benchmark dataset show that the method gets close to current state-of-the-art methods in terms of localization accuracy even though these make use of multiple frames. Furthermore, we created a more challenging and realistic dataset with multiple object categories and varying viewpoint and illumination conditions for evaluating the method's performance in real world scenarios." @default.
- W2796972250 created "2018-04-24" @default.
- W2796972250 creator A5000623134 @default.
- W2796972250 creator A5028082686 @default.
- W2796972250 date "2018-04-11" @default.
- W2796972250 modified "2023-09-27" @default.
- W2796972250 title "Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization." @default.
- W2796972250 cites W1521527082 @default.
- W2796972250 cites W1567556022 @default.
- W2796972250 cites W1607939233 @default.
- W2796972250 cites W1974548235 @default.
- W2796972250 cites W1974843892 @default.
- W2796972250 cites W1996140089 @default.
- W2796972250 cites W2016016818 @default.
- W2796972250 cites W2093334045 @default.
- W2796972250 cites W2108598243 @default.
- W2796972250 cites W2112301665 @default.
- W2796972250 cites W2142850760 @default.
- W2796972250 cites W2167764260 @default.
- W2796972250 cites W2613718673 @default.
- W2796972250 cites W2619538244 @default.
- W2796972250 cites W2765469267 @default.
- W2796972250 cites W2950800384 @default.
- W2796972250 cites W2950926078 @default.
- W2796972250 hasPublicationYear "2018" @default.
- W2796972250 type Work @default.
- W2796972250 sameAs 2796972250 @default.
- W2796972250 citedByCount "3" @default.
- W2796972250 countsByYear W27969722502018 @default.
- W2796972250 countsByYear W27969722502020 @default.
- W2796972250 countsByYear W27969722502021 @default.
- W2796972250 crossrefType "posted-content" @default.
- W2796972250 hasAuthorship W2796972250A5000623134 @default.
- W2796972250 hasAuthorship W2796972250A5028082686 @default.
- W2796972250 hasConcept C103278499 @default.
- W2796972250 hasConcept C111919701 @default.
- W2796972250 hasConcept C115961682 @default.
- W2796972250 hasConcept C118505674 @default.
- W2796972250 hasConcept C153180895 @default.
- W2796972250 hasConcept C154945302 @default.
- W2796972250 hasConcept C185798385 @default.
- W2796972250 hasConcept C205649164 @default.
- W2796972250 hasConcept C2777212361 @default.
- W2796972250 hasConcept C2779679900 @default.
- W2796972250 hasConcept C2780719617 @default.
- W2796972250 hasConcept C2781238097 @default.
- W2796972250 hasConcept C31972630 @default.
- W2796972250 hasConcept C41008148 @default.
- W2796972250 hasConcept C58640448 @default.
- W2796972250 hasConcept C8038995 @default.
- W2796972250 hasConceptScore W2796972250C103278499 @default.
- W2796972250 hasConceptScore W2796972250C111919701 @default.
- W2796972250 hasConceptScore W2796972250C115961682 @default.
- W2796972250 hasConceptScore W2796972250C118505674 @default.
- W2796972250 hasConceptScore W2796972250C153180895 @default.
- W2796972250 hasConceptScore W2796972250C154945302 @default.
- W2796972250 hasConceptScore W2796972250C185798385 @default.
- W2796972250 hasConceptScore W2796972250C205649164 @default.
- W2796972250 hasConceptScore W2796972250C2777212361 @default.
- W2796972250 hasConceptScore W2796972250C2779679900 @default.
- W2796972250 hasConceptScore W2796972250C2780719617 @default.
- W2796972250 hasConceptScore W2796972250C2781238097 @default.
- W2796972250 hasConceptScore W2796972250C31972630 @default.
- W2796972250 hasConceptScore W2796972250C41008148 @default.
- W2796972250 hasConceptScore W2796972250C58640448 @default.
- W2796972250 hasConceptScore W2796972250C8038995 @default.
- W2796972250 hasLocation W27969722501 @default.
- W2796972250 hasOpenAccess W2796972250 @default.
- W2796972250 hasPrimaryLocation W27969722501 @default.
- W2796972250 hasRelatedWork W1969653662 @default.
- W2796972250 hasRelatedWork W2093573905 @default.
- W2796972250 hasRelatedWork W2152513128 @default.
- W2796972250 hasRelatedWork W2400092189 @default.
- W2796972250 hasRelatedWork W2422471819 @default.
- W2796972250 hasRelatedWork W2566793769 @default.
- W2796972250 hasRelatedWork W2577132299 @default.
- W2796972250 hasRelatedWork W2783847366 @default.
- W2796972250 hasRelatedWork W2900227785 @default.
- W2796972250 hasRelatedWork W2944040903 @default.
- W2796972250 hasRelatedWork W2952229497 @default.
- W2796972250 hasRelatedWork W2952289000 @default.
- W2796972250 hasRelatedWork W2961348656 @default.
- W2796972250 hasRelatedWork W2964215765 @default.
- W2796972250 hasRelatedWork W2964915061 @default.
- W2796972250 hasRelatedWork W2982081451 @default.
- W2796972250 hasRelatedWork W3013211900 @default.
- W2796972250 hasRelatedWork W3081437849 @default.
- W2796972250 hasRelatedWork W3098241816 @default.
- W2796972250 hasRelatedWork W3108602871 @default.
- W2796972250 isParatext "false" @default.
- W2796972250 isRetracted "false" @default.
- W2796972250 magId "2796972250" @default.
- W2796972250 workType "article" @default.