Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951746655> ?p ?o ?g. }
- W2951746655 abstract "We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the entire object area. Our goal is to overcome this limitation with no additional human intervention by retrieving videos relevant to target class labels from web repository, and generating segmentation labels from the retrieved videos to simulate strong supervision for semantic segmentation. During this process, we take advantage of image classification with discriminative localization technique to reject false alarms in retrieved videos and identify relevant spatio-temporal volumes within retrieved videos. Although the entire procedure does not require any additional supervision, the segmentation annotations obtained from videos are sufficiently strong to learn a model for semantic segmentation. The proposed algorithm substantially outperforms existing methods based on the same level of supervision and is even as competitive as the approaches relying on extra annotations." @default.
- W2951746655 created "2019-06-27" @default.
- W2951746655 creator A5006594639 @default.
- W2951746655 creator A5041811209 @default.
- W2951746655 creator A5060343759 @default.
- W2951746655 creator A5064419280 @default.
- W2951746655 creator A5077461583 @default.
- W2951746655 date "2017-01-02" @default.
- W2951746655 modified "2023-10-16" @default.
- W2951746655 title "Weakly Supervised Semantic Segmentation using Web-Crawled Videos" @default.
- W2951746655 cites W1529410181 @default.
- W2951746655 cites W1783315696 @default.
- W2951746655 cites W1903029394 @default.
- W2951746655 cites W1920142129 @default.
- W2951746655 cites W1931270512 @default.
- W2951746655 cites W1945608308 @default.
- W2951746655 cites W1964763677 @default.
- W2951746655 cites W1973054923 @default.
- W2951746655 cites W2031489346 @default.
- W2951746655 cites W2081613070 @default.
- W2951746655 cites W2105297725 @default.
- W2951746655 cites W2108598243 @default.
- W2951746655 cites W2111077768 @default.
- W2951746655 cites W2113708607 @default.
- W2951746655 cites W2124351162 @default.
- W2951746655 cites W2140199336 @default.
- W2951746655 cites W2257483379 @default.
- W2951746655 cites W2295107390 @default.
- W2951746655 cites W2306289963 @default.
- W2951746655 cites W2337429362 @default.
- W2951746655 cites W2338138401 @default.
- W2951746655 cites W2474309084 @default.
- W2951746655 cites W2501943378 @default.
- W2951746655 cites W2508741746 @default.
- W2951746655 cites W2517104666 @default.
- W2951746655 cites W2949086864 @default.
- W2951746655 cites W2949847866 @default.
- W2951746655 cites W2950094539 @default.
- W2951746655 cites W2950931866 @default.
- W2951746655 cites W2952637581 @default.
- W2951746655 cites W2962835968 @default.
- W2951746655 cites W2964121744 @default.
- W2951746655 cites W2964288706 @default.
- W2951746655 cites W589665618 @default.
- W2951746655 cites W611457968 @default.
- W2951746655 doi "https://doi.org/10.48550/arxiv.1701.00352" @default.
- W2951746655 hasPublicationYear "2017" @default.
- W2951746655 type Work @default.
- W2951746655 sameAs 2951746655 @default.
- W2951746655 citedByCount "20" @default.
- W2951746655 countsByYear W29517466552017 @default.
- W2951746655 countsByYear W29517466552018 @default.
- W2951746655 countsByYear W29517466552019 @default.
- W2951746655 countsByYear W29517466552020 @default.
- W2951746655 countsByYear W29517466552021 @default.
- W2951746655 crossrefType "posted-content" @default.
- W2951746655 hasAuthorship W2951746655A5006594639 @default.
- W2951746655 hasAuthorship W2951746655A5041811209 @default.
- W2951746655 hasAuthorship W2951746655A5060343759 @default.
- W2951746655 hasAuthorship W2951746655A5064419280 @default.
- W2951746655 hasAuthorship W2951746655A5077461583 @default.
- W2951746655 hasBestOaLocation W29517466551 @default.
- W2951746655 hasConcept C111919701 @default.
- W2951746655 hasConcept C119857082 @default.
- W2951746655 hasConcept C124504099 @default.
- W2951746655 hasConcept C153180895 @default.
- W2951746655 hasConcept C154945302 @default.
- W2951746655 hasConcept C2777212361 @default.
- W2951746655 hasConcept C2781238097 @default.
- W2951746655 hasConcept C41008148 @default.
- W2951746655 hasConcept C89600930 @default.
- W2951746655 hasConcept C97931131 @default.
- W2951746655 hasConcept C98045186 @default.
- W2951746655 hasConceptScore W2951746655C111919701 @default.
- W2951746655 hasConceptScore W2951746655C119857082 @default.
- W2951746655 hasConceptScore W2951746655C124504099 @default.
- W2951746655 hasConceptScore W2951746655C153180895 @default.
- W2951746655 hasConceptScore W2951746655C154945302 @default.
- W2951746655 hasConceptScore W2951746655C2777212361 @default.
- W2951746655 hasConceptScore W2951746655C2781238097 @default.
- W2951746655 hasConceptScore W2951746655C41008148 @default.
- W2951746655 hasConceptScore W2951746655C89600930 @default.
- W2951746655 hasConceptScore W2951746655C97931131 @default.
- W2951746655 hasConceptScore W2951746655C98045186 @default.
- W2951746655 hasLocation W29517466551 @default.
- W2951746655 hasOpenAccess W2951746655 @default.
- W2951746655 hasPrimaryLocation W29517466551 @default.
- W2951746655 hasRelatedWork W1562793155 @default.
- W2951746655 hasRelatedWork W1652783584 @default.
- W2951746655 hasRelatedWork W1940903118 @default.
- W2951746655 hasRelatedWork W2005476934 @default.
- W2951746655 hasRelatedWork W2510758617 @default.
- W2951746655 hasRelatedWork W2799124825 @default.
- W2951746655 hasRelatedWork W2897195263 @default.
- W2951746655 hasRelatedWork W4224853195 @default.
- W2951746655 hasRelatedWork W74886973 @default.
- W2951746655 hasRelatedWork W1967061043 @default.
- W2951746655 isParatext "false" @default.
- W2951746655 isRetracted "false" @default.
- W2951746655 magId "2951746655" @default.