{"id":"https://openalex.org/W2158427031","doi":"https://doi.org/10.1109/iccv.2011.6126299","title":"Weakly supervised semantic segmentation with a multi-image model","display_name":"Weakly supervised semantic segmentation with a multi-image model","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2158427031","doi":"https://doi.org/10.1109/iccv.2011.6126299","mag":"2158427031"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2011.6126299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2011.6126299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Computer Vision","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/1bd180cd-11bc-4323-b506-a8f119cbe55c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019603588","display_name":"Alexander Vezhnevets","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alexander Vezhnevets","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423778","display_name":"Vittorio Ferrari","orcid":"https://orcid.org/0000-0002-1942-233X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vittorio Ferrari","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038199211","display_name":"Joachim M. Buhmann","orcid":"https://orcid.org/0000-0002-6613-7101"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Joachim M. Buhmann","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5145,"has_fulltext":false,"cited_by_count":158,"citation_normalized_percentile":{"value":0.98894754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8111312389373779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735332727432251},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6675791144371033},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6513972878456116},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6383376121520996},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6258602142333984},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5317593812942505},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4950193762779236},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47829657793045044},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47377681732177734},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44626492261886597},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3940388262271881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19242966175079346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10701102018356323}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8111312389373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735332727432251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6675791144371033},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6513972878456116},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6383376121520996},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6258602142333984},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5317593812942505},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4950193762779236},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47829657793045044},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47377681732177734},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44626492261886597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3940388262271881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19242966175079346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10701102018356323},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iccv.2011.6126299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2011.6126299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Computer Vision","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.8391","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.8391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.inf.ed.ac.uk/calvin/Publications/vezhnevets11iccv.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.6134","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.6134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.inf.ed.ac.uk/calvin/hp_avezhnev/Pubs/WeaklySupSemSeg.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1bd180cd-11bc-4323-b506-a8f119cbe55c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1bd180cd-11bc-4323-b506-a8f119cbe55c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vezhnevets, A, Ferrari, V & Buhmann, J M 2011, Weakly supervised semantic segmentation with a multi-image model. in Computer Vision (ICCV), 2011 IEEE International Conference on. pp. 643-650. https://doi.org/10.1109/ICCV.2011.6126299","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1bd180cd-11bc-4323-b506-a8f119cbe55c","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6126299&tag=1","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/1bd180cd-11bc-4323-b506-a8f119cbe55c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1bd180cd-11bc-4323-b506-a8f119cbe55c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vezhnevets, A, Ferrari, V & Buhmann, J M 2011, Weakly supervised semantic segmentation with a multi-image model. in Computer Vision (ICCV), 2011 IEEE International Conference on. pp. 643-650. https://doi.org/10.1109/ICCV.2011.6126299","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1528789833","https://openalex.org/W1566135517","https://openalex.org/W1666447063","https://openalex.org/W1748750709","https://openalex.org/W1952794764","https://openalex.org/W1994259434","https://openalex.org/W2020636921","https://openalex.org/W2029731618","https://openalex.org/W2100588357","https://openalex.org/W2101309634","https://openalex.org/W2113137767","https://openalex.org/W2116877738","https://openalex.org/W2117132237","https://openalex.org/W2119531662","https://openalex.org/W2123023145","https://openalex.org/W2124386111","https://openalex.org/W2125849446","https://openalex.org/W2128715914","https://openalex.org/W2134529554","https://openalex.org/W2143516773","https://openalex.org/W2149954907","https://openalex.org/W2155871590","https://openalex.org/W2162915993","https://openalex.org/W2535516436","https://openalex.org/W2536305071","https://openalex.org/W4252621450","https://openalex.org/W6631412525","https://openalex.org/W6637249095","https://openalex.org/W6637730771","https://openalex.org/W6640860105","https://openalex.org/W6677634198","https://openalex.org/W6678684981"],"related_works":["https://openalex.org/W4285411112","https://openalex.org/W2085033728","https://openalex.org/W2171299904","https://openalex.org/W4390494008","https://openalex.org/W2922442631","https://openalex.org/W2053596378","https://openalex.org/W2168523118","https://openalex.org/W2073639911","https://openalex.org/W2106540031","https://openalex.org/W2047970610"],"abstract_inverted_index":{"We":[0,105],"propose":[1],"a":[2,34,44,49,70,90],"novel":[3],"method":[4,32],"for":[5,37,52],"weakly":[6,143],"supervised":[7,144,152],"semantic":[8],"segmentation.":[9],"Training":[10],"images":[11,29,68,83],"are":[12],"labeled":[13],"only":[14],"by":[15,21],"the":[16,25,31,54,58,101,129,134],"classes":[17,121],"they":[18],"contain,":[19],"not":[20],"their":[22,75],"location":[23],"in":[24,69],"image.":[26],"On":[27],"test":[28,82],"instead,":[30],"predicts":[33],"class":[35],"label":[36],"every":[38],"pixel.":[39],"Our":[40],"main":[41],"innovation":[42],"is":[43],"multi-image":[45],"model":[46,51,62],"(MIM)":[47],"-":[48],"graphical":[50],"recovering":[53],"pixel":[55,103],"labels":[56],"of":[57,96,137],"training":[59,67],"images.":[60],"The":[61],"connects":[63],"superpixels":[64],"from":[65,119],"all":[66],"data-driven":[71],"fashion,":[72],"based":[73],"on":[74,100,128],"appearance":[76],"similarity.":[77],"For":[78],"generalizing":[79],"to":[80],"new":[81],"we":[84],"integrate":[85],"them":[86],"into":[87],"MIM":[88],"using":[89],"learned":[91],"multiple":[92],"kernel":[93],"metric,":[94],"instead":[95],"learning":[97],"conventional":[98],"classifiers":[99],"recovered":[102],"labels.":[104],"also":[106],"introduce":[107],"an":[108],"\u201cobjectness\u201d":[109],"potential,":[110],"that":[111],"helps":[112],"separating":[113],"objects":[114],"(e.g.":[115,122],"car,":[116],"dog,":[117],"human)":[118],"background":[120],"grass,":[123],"sky,":[124],"road).":[125],"In":[126],"experiments":[127],"MSRC":[130],"21":[131],"dataset":[132],"and":[133,146],"LabelMe":[135],"subset":[136],"[18],":[138],"our":[139],"technique":[140],"outperforms":[141],"previous":[142],"methods":[145],"achieves":[147],"accuracy":[148],"comparable":[149],"with":[150],"fully":[151],"methods.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}