{"id":"https://openalex.org/W4413887037","doi":"https://doi.org/10.1109/tmm.2025.3604944","title":"CollabLearn: Propelling Weakly-Supervised Referring Image Segmentation Through Collaboration Between Semantics and Details","display_name":"CollabLearn: Propelling Weakly-Supervised Referring Image Segmentation Through Collaboration Between Semantics and Details","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413887037","doi":"https://doi.org/10.1109/tmm.2025.3604944"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3604944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3604944","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Chao Jiang","orcid":"https://orcid.org/0009-0009-9680-9624"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Jiang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0009-9680-9624","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065172324","display_name":"Yuqiu Kong","orcid":"https://orcid.org/0000-0003-2168-204X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiu Kong","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-2168-204X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027718772","display_name":"Mengnan Zhao","orcid":"https://orcid.org/0000-0001-8319-4266"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengnan Zhao","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-8319-4266","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015500789","display_name":"Lihe Zhang","orcid":"https://orcid.org/0000-0002-9241-1688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihe Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9241-1688","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088269837","display_name":"Baocai Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18158608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"8045","last_page":"8055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9613000154495239,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9613000154495239,"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":0.9398999810218811,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9383000135421753,"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/computer-science","display_name":"Computer science","score":0.8201342821121216},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6913769245147705},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6565799713134766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351340174674988},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5191892385482788},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4265681505203247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38228556513786316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3618435859680176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.344206839799881},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11441707611083984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201342821121216},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6913769245147705},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6565799713134766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351340174674988},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5191892385482788},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4265681505203247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38228556513786316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3618435859680176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.344206839799881},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11441707611083984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3604944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3604944","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2300386902","display_name":null,"funder_award_id":"62276046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2315529589","display_name":null,"funder_award_id":"62406055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3064143480","display_name":null,"funder_award_id":"62431004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2103559027","https://openalex.org/W2108598243","https://openalex.org/W2489434015","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2915623326","https://openalex.org/W2962858109","https://openalex.org/W2963109634","https://openalex.org/W2963145877","https://openalex.org/W2963150697","https://openalex.org/W2963445828","https://openalex.org/W2964345792","https://openalex.org/W2964935470","https://openalex.org/W2967186499","https://openalex.org/W2981663434","https://openalex.org/W2987401211","https://openalex.org/W3034368090","https://openalex.org/W3035703639","https://openalex.org/W3117585461","https://openalex.org/W3126391825","https://openalex.org/W3178418424","https://openalex.org/W3201770677","https://openalex.org/W3207558419","https://openalex.org/W4200631575","https://openalex.org/W4224988000","https://openalex.org/W4225517085","https://openalex.org/W4283688199","https://openalex.org/W4311138681","https://openalex.org/W4312330522","https://openalex.org/W4312521487","https://openalex.org/W4386065432","https://openalex.org/W4386076034","https://openalex.org/W4386076148","https://openalex.org/W4386108423","https://openalex.org/W4390871756","https://openalex.org/W4390871886","https://openalex.org/W4390873170","https://openalex.org/W4390873528","https://openalex.org/W4390873641","https://openalex.org/W4390874575","https://openalex.org/W4390874680","https://openalex.org/W4391164254","https://openalex.org/W4393149030","https://openalex.org/W4393149082","https://openalex.org/W4402727539"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W3112772842","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,82,87,106,124,138],"weakly":[4,168],"supervised":[5,169],"referring":[6,20,33],"image":[7],"segmentation":[8,47,133],"method,":[9],"named":[10],"<italic":[11],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[12],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CollabLearn</i>,":[13],"that":[14,163],"segments":[15],"objects":[16,50,136],"described":[17],"by":[18],"free-form":[19],"expression":[21],"utilizing":[22],"solely":[23],"image-text":[24],"pairs.":[25],"Existing":[26],"methods":[27],"suffer":[28],"from":[29,52],"incorrect":[30],"localization":[31,122],"of":[32,39,48,55,92,134],"expressions":[34],"due":[35],"to":[36,147],"the":[37,53,111,132],"lack":[38],"high-level":[40,73],"semantics":[41,74],"in":[42,123,137],"cross-modal":[43,69,117],"alignment":[44],"or":[45],"rough":[46],"referenced":[49],"stemming":[51],"absence":[54],"low-level":[56,76],"details.":[57],"To":[58],"address":[59],"these":[60,93,151],"issues,":[61],"we":[62],"propose":[63],"an":[64,96],"innovative":[65],"framework":[66],"for":[67],"generating":[68],"features":[70],"encompassing":[71],"both":[72],"and":[75,86,99,119],"details":[77],"via":[78],"two":[79,152],"fusion":[80],"modules:":[81],"semantic":[83,112],"awareness":[84,113],"module":[85,114,130],"detail":[88,128],"cognition":[89,129],"module.":[90],"Each":[91],"modules":[94],"generates":[95],"activation":[97],"map,":[98],"they":[100],"mutually":[101],"correct":[102],"each":[103],"other":[104],"through":[105],"collaborative":[107,142],"learning":[108,143],"strategy.":[109],"Specifically,":[110],"performs":[115],"in-depth":[116],"interaction":[118,149],"achieves":[120],"accurate":[121],"top-down":[125],"manner.":[126,140],"The":[127],"facilitates":[131],"entire":[135],"bottom-up":[139],"A":[141],"strategy":[144],"is":[145],"designed":[146],"enable":[148],"between":[150],"modules,":[153],"enforcing":[154],"sufficient":[155],"vision-language":[156],"alignment.":[157],"Experiments":[158],"on":[159],"three":[160],"benchmarks":[161],"demonstrate":[162],"CollabLearn":[164],"consistently":[165],"outperforms":[166],"state-of-the-art":[167],"methods.":[170]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
