{"id":"https://openalex.org/W4402979952","doi":"https://doi.org/10.1109/icme57554.2024.10687826","title":"Towards Omni-supervised Referring Expression Segmentation","display_name":"Towards Omni-supervised Referring Expression Segmentation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979952","doi":"https://doi.org/10.1109/icme57554.2024.10687826"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029317372","display_name":"Minglang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglang Huang","raw_affiliation_strings":["Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020568230","display_name":"Guannan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guannan Jiang","raw_affiliation_strings":["Contemporary Amperex Technology Co. Limited (CATL),Intelligent Manufacturing Department,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co. Limited (CATL),Intelligent Manufacturing Department,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089635653","display_name":"Weilin Zhuang","orcid":"https://orcid.org/0009-0001-6940-8384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Zhuang","raw_affiliation_strings":["Contemporary Amperex Technology Co. Limited (CATL),Intelligent Manufacturing Department,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co. Limited (CATL),Intelligent Manufacturing Department,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education of China, Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17077402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9915000200271606,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9812999963760376,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661948025226593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6000791788101196},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5532033443450928},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5301569104194641},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4326592981815338},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38935038447380066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.374721884727478},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3357961177825928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661948025226593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000791788101196},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5532033443450928},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5301569104194641},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4326592981815338},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38935038447380066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.374721884727478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3357961177825928},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2295107390","https://openalex.org/W2489434015","https://openalex.org/W2963150697","https://openalex.org/W2964284374","https://openalex.org/W2989868392","https://openalex.org/W3034930876","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3107653507","https://openalex.org/W3107730255","https://openalex.org/W3170602832","https://openalex.org/W3172507542","https://openalex.org/W3174965650","https://openalex.org/W3175722450","https://openalex.org/W3187664142","https://openalex.org/W3203354307","https://openalex.org/W3206582857","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4224304134","https://openalex.org/W4224988000","https://openalex.org/W4294310675","https://openalex.org/W4307504011","https://openalex.org/W4309181071","https://openalex.org/W4312543911","https://openalex.org/W4313141979","https://openalex.org/W4386075493","https://openalex.org/W4386076142","https://openalex.org/W6681075545","https://openalex.org/W6694395031","https://openalex.org/W6733814495","https://openalex.org/W6776778719","https://openalex.org/W6784163774","https://openalex.org/W6789505266","https://openalex.org/W6804418671","https://openalex.org/W6838088247","https://openalex.org/W6847684288"],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W4379231730","https://openalex.org/W3129895999","https://openalex.org/W2328518092","https://openalex.org/W4389858081","https://openalex.org/W3101249758","https://openalex.org/W2382079200","https://openalex.org/W2374091470","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referring":[0,41],"Expression":[1,42],"Segmentation":[2,43],"(RES)":[3],"is":[4,67,156],"a":[5,35,70,143],"challenging":[6],"task":[7,38],"in":[8,147],"computer":[9],"vision":[10],"that":[11],"involves":[12],"segmenting":[13],"image":[14],"instances":[15],"using":[16,131],"textual":[17],"descriptions.":[18],"Conventional":[19],"approaches":[20],"suffer":[21],"from":[22],"the":[23,78,122],"high":[24],"cost":[25],"of":[26,82,124],"acquiring":[27],"segmentation":[28],"labels.":[29],"To":[30],"overcome":[31],"this,":[32],"we":[33],"propose":[34],"novel":[36],"learning":[37,72],"called":[39],"Omni-supervised":[40],"(Omni-RES)":[44],"which":[45],"leverages":[46],"unlabeled,":[47],"fully":[48,116],"labeled,":[49],"and":[50,80,102,109],"weakly":[51],"labeled":[52,117],"data,":[53,118],"such":[54,149],"as":[55,90,150],"referring":[56],"points":[57],"or":[58],"bounding":[59],"boxes,":[60],"for":[61,85,138],"efficient":[62],"RES":[63,100,140],"training.":[64,127],"Our":[65,154],"approach":[66],"based":[68],"on":[69,97,152],"teacher-student":[71],"framework,":[73],"where":[74],"weak":[75],"labels":[76],"guide":[77],"selection":[79],"refinement":[81],"high-quality":[83],"pseudo-masks":[84],"training,":[86,141],"rather":[87],"than":[88],"serving":[89],"direct":[91],"supervision":[92],"signals.":[93],"We":[94],"tested":[95],"Omni-RES":[96,119],"various":[98],"state-of-the-art":[99,145],"models":[101],"datasets,":[103],"demonstrating":[104],"its":[105],"superiority":[106],"over":[107],"fully-supervised":[108],"semi-supervised":[110],"methods.":[111],"Remarkably,":[112],"with":[113],"just":[114],"10%":[115],"can":[120],"match":[121],"performance":[123,146],"100%":[125],"supervised":[126],"Additionally,":[128],"it":[129],"enables":[130],"large-scale":[132],"vision-language":[133],"datasets":[134],"like":[135],"Visual":[136],"Genome":[137],"cost-effective":[139],"setting":[142],"new":[144],"RES,":[148],"80.66":[151],"RefCOCO.":[153],"code":[155],"released":[157],"at:":[158],"https://github.com/nineblu/omni-res":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}