{"id":"https://openalex.org/W3002047086","doi":"https://doi.org/10.24963/ijcai.2020/120","title":"Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings","display_name":"Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3002047086","doi":"https://doi.org/10.24963/ijcai.2020/120","mag":"3002047086"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/120","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/120","pdf_url":"https://www.ijcai.org/proceedings/2020/0120.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0120.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022335103","display_name":"Mennatullah Siam","orcid":"https://orcid.org/0000-0003-1854-3698"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mennatullah Siam","raw_affiliation_strings":["HiSilicon, Huawei Research","University of Alberta"],"affiliations":[{"raw_affiliation_string":"HiSilicon, Huawei Research","institution_ids":[]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008900816","display_name":"Naren Doraiswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Naren Doraiswamy","raw_affiliation_strings":["Indian Institute of Science"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012459174","display_name":"Boris N. Oreshkin","orcid":"https://orcid.org/0000-0002-1869-2004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris N. Oreshkin","raw_affiliation_strings":["Element AI"],"affiliations":[{"raw_affiliation_string":"Element AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050876115","display_name":"Hengshuai Yao","orcid":"https://orcid.org/0000-0003-1258-1845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengshuai Yao","raw_affiliation_strings":["HiSilicon, Huawei Research"],"affiliations":[{"raw_affiliation_string":"HiSilicon, Huawei Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948380","display_name":"Martin J\u00e4gersand","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Jagersand","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022335103"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.6857,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75642634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9986000061035156,"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":0.9973000288009644,"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/segmentation","display_name":"Segmentation","score":0.8142819404602051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7591871023178101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497868537902832},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6599209308624268},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6328622102737427},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6102071404457092},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6083388924598694},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5492725372314453},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5399236083030701},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5271776914596558},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4968412220478058},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.47217172384262085},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4215092658996582},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.41847318410873413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40879756212234497},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31158682703971863}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8142819404602051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7591871023178101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497868537902832},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6599209308624268},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6328622102737427},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6102071404457092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6083388924598694},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5492725372314453},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5399236083030701},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5271776914596558},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4968412220478058},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.47217172384262085},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4215092658996582},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.41847318410873413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40879756212234497},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31158682703971863},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2020/120","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/120","pdf_url":"https://www.ijcai.org/proceedings/2020/0120.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.09540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09540","pdf_url":"https://arxiv.org/pdf/2001.09540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2001.09540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.09540","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3002047086","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/120","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/120","pdf_url":"https://www.ijcai.org/proceedings/2020/0120.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3002047086.pdf","grobid_xml":"https://content.openalex.org/works/W3002047086.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2037227137","https://openalex.org/W2108598243","https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2630837129","https://openalex.org/W2754560798","https://openalex.org/W2890447039","https://openalex.org/W2893918048","https://openalex.org/W2902683551","https://openalex.org/W2950133940","https://openalex.org/W2952355813","https://openalex.org/W2955084925","https://openalex.org/W2963599420","https://openalex.org/W2963668159","https://openalex.org/W2963954913","https://openalex.org/W2967857025","https://openalex.org/W2979062293","https://openalex.org/W2983850069","https://openalex.org/W2990230185","https://openalex.org/W2994528761","https://openalex.org/W2997490332","https://openalex.org/W3089109144"],"related_works":["https://openalex.org/W3119507534","https://openalex.org/W2997884746","https://openalex.org/W3170973447","https://openalex.org/W3153674976","https://openalex.org/W3209086464","https://openalex.org/W3202877682","https://openalex.org/W3108187451","https://openalex.org/W3000932375","https://openalex.org/W3090986860","https://openalex.org/W2969082793","https://openalex.org/W3149878926","https://openalex.org/W2971113548","https://openalex.org/W3106029750","https://openalex.org/W3166448862","https://openalex.org/W3008076364","https://openalex.org/W3187597655","https://openalex.org/W2924485953","https://openalex.org/W3016034512","https://openalex.org/W2962957359","https://openalex.org/W3168978642"],"abstract_inverted_index":{"Significant":[0],"progress":[1],"has":[2],"been":[3],"made":[4],"recently":[5],"in":[6,18,154],"developing":[7],"few-shot":[8,19,40,51,77,97,111],"object":[9,41,52,78],"segmentation":[10,20,53,98,112],"methods.":[11],"Learning":[12,134],"is":[13],"shown":[14],"to":[15,109],"be":[16,140],"successful":[17],"settings,":[21],"using":[22,59,67,113],"pixel-level,":[23],"scribbles":[24],"and":[25,62,104,157],"bounding":[26,88],"box":[27,89],"supervision.":[28],"This":[29],"paper":[30],"takes":[31],"another":[32],"approach,":[33],"i.e.,":[34],"only":[35],"requiring":[36],"image-level":[37,68,76,121],"label":[38],"for":[39,50,132,136],"segmentation.":[42,79],"We":[43,123],"propose":[44,125],"a":[45,56,126,143],"novel":[46,127],"multi-modal":[47],"interaction":[48],"module":[49],"that":[54,85,96,105],"utilizes":[55],"co-attention":[57],"mechanism":[58],"both":[60,155],"visual":[61,116],"word":[63,102],"embedding.":[64],"Our":[65,93],"model":[66],"labels":[69],"achieves":[70],"4.8%":[71],"improvement":[72],"over":[73],"previously":[74],"proposed":[75],"It":[80],"also":[81],"outperforms":[82],"state-of-the-art":[83],"methods":[84],"use":[86],"weak":[87,120],"supervision":[90],"on":[91,142],"PASCAL-5^i.":[92],"results":[94],"show":[95],"benefits":[99],"from":[100],"utilizing":[101],"embeddings,":[103],"we":[106],"are":[107],"able":[108],"perform":[110],"stacked":[114],"joint":[115],"semantic":[117],"processing":[118],"with":[119],"labels.":[122],"further":[124],"setup,":[128],"Temporal":[129],"Object":[130],"Segmentation":[131],"Few-shot":[133],"(TOSFL)":[135],"videos.":[137],"TOSFL":[138,159],"can":[139],"used":[141],"variety":[144],"of":[145],"public":[146],"video":[147],"data":[148],"such":[149],"as":[150,152],"Youtube-VOS,":[151],"demonstrated":[153],"instance-level":[156],"category-level":[158],"experiments.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}