{"id":"https://openalex.org/W4405717807","doi":"https://doi.org/10.1109/tmm.2024.3521741","title":"Weakly Supervised Referring Video Object Segmentation With Object-Centric Pseudo-Guidance","display_name":"Weakly Supervised Referring Video Object Segmentation With Object-Centric Pseudo-Guidance","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405717807","doi":"https://doi.org/10.1109/tmm.2024.3521741"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521741","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":"Weikang Wang","orcid":"https://orcid.org/0000-0001-5165-204X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikang Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","School of Electrical and Information Engineering, Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0001-5165-204X","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuting Su","orcid":"https://orcid.org/0000-0001-9591-8559"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","School of Electrical and Information Engineering, Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0001-9591-8559","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","School of Electrical and Information Engineering, Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0003-4690-1886","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044700284","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0001-8162-1949"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8162-1949","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","MoE Key Laboratory of Artificial Intelligence, the AI Institute, and the Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, the AI Institute, and the Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.6101,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66555616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"1320","last_page":"1333"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9951000213623047,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9930999875068665,"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":0.8630070686340332},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6606110334396362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568446755409241},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6325206756591797},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6142702102661133},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5247167348861694},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4210375249385834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8630070686340332},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6606110334396362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568446755409241},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6325206756591797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6142702102661133},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5247167348861694},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4210375249385834}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521741","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/G173205433","display_name":null,"funder_award_id":"U21B2024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3007184350","display_name":null,"funder_award_id":"62371333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5632917453","display_name":null,"funder_award_id":"62371330","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W611457968","https://openalex.org/W2034014085","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2953920664","https://openalex.org/W2963072537","https://openalex.org/W2963311325","https://openalex.org/W2963354481","https://openalex.org/W2980088508","https://openalex.org/W2982093251","https://openalex.org/W2983693499","https://openalex.org/W2997063389","https://openalex.org/W3026441479","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3106546328","https://openalex.org/W3107730255","https://openalex.org/W3108432914","https://openalex.org/W3168822201","https://openalex.org/W3174598330","https://openalex.org/W3177892185","https://openalex.org/W3178075329","https://openalex.org/W3180169285","https://openalex.org/W3207409917","https://openalex.org/W3214586131","https://openalex.org/W3215899623","https://openalex.org/W4205268584","https://openalex.org/W4221167637","https://openalex.org/W4226024706","https://openalex.org/W4293464712","https://openalex.org/W4312322023","https://openalex.org/W4312578467","https://openalex.org/W4312690830","https://openalex.org/W4312872987","https://openalex.org/W4312981390","https://openalex.org/W4313145515","https://openalex.org/W4318035685","https://openalex.org/W4320713023","https://openalex.org/W4386071623","https://openalex.org/W4386076180","https://openalex.org/W4387969140","https://openalex.org/W4388081044","https://openalex.org/W4389524050","https://openalex.org/W4390871749","https://openalex.org/W4390872868","https://openalex.org/W4390873204","https://openalex.org/W4390874496","https://openalex.org/W4390874575","https://openalex.org/W6620707391","https://openalex.org/W6767465851","https://openalex.org/W6792105337","https://openalex.org/W6851407990","https://openalex.org/W6852629184"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2385949326","https://openalex.org/W2623195638","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725","https://openalex.org/W2185534064"],"abstract_inverted_index":{"Referring":[0],"video":[1,11,59],"object":[2,19,60,70,102,115,145],"segmentation":[3,61],"(RVOS)":[4],"is":[5,89,109,139],"an":[6,83],"emerging":[7],"task":[8],"for":[9,96],"multimodal":[10,133],"comprehension":[12],"while":[13],"the":[14,22,31,97,114,144,176],"expensive":[15,34],"annotating":[16],"process":[17],"of":[18,26,100,119],"masks":[20],"restricts":[21],"scalability":[23],"and":[24,37,72,122,151,170,185],"diversity":[25],"RVOS":[27,53,162],"datasets.":[28],"To":[29],"relax":[30],"dependency":[32],"on":[33,158],"mask":[35,86],"annotations":[36],"take":[38],"advantage":[39],"from":[40],"large-scale":[41],"partially":[42],"annotated":[43],"data,":[44],"in":[45,117,182],"this":[46],"paper,":[47],"we":[48,76],"explore":[49],"a":[50,78,105,126,132],"novel":[51],"extended":[52],"task,":[54],"namely":[55],"weakly":[56],"supervised":[57],"referring":[58],"(WRVOS),":[62],"which":[63],"employs":[64],"multiple":[65],"weak":[66],"supervision":[67],"sources,":[68],"including":[69,164],"points":[71],"bounding":[73],"boxes.":[74],"Correspondingly,":[75],"propose":[77],"unified":[79],"WRVOS":[80],"framework.":[81],"Specifically,":[82],"object-centric":[84],"pseudo":[85,98],"generation":[87],"method":[88,138,178],"introduced":[90],"to":[91,111,141],"provide":[92],"effective":[93],"shape":[94],"priors":[95],"guidance":[99],"spatial":[101,120],"location.":[103],"Then,":[104],"pseudo-guided":[106],"optimization":[107],"strategy":[108],"proposed":[110,140,177],"effectively":[112],"optimize":[113],"outlines":[116],"terms":[118],"location":[121],"projection":[123],"density":[124],"with":[125],"multi-stage":[127],"online":[128],"learning":[129],"strategy.":[130],"Furthermore,":[131],"cross-frame":[134],"level":[135],"set":[136],"evolution":[137],"iteratively":[142],"refine":[143],"boundaries":[146],"considering":[147],"both":[148,183],"temporal":[149],"consistency":[150],"cross-modal":[152],"interactions.":[153],"Extensive":[154],"experiments":[155],"are":[156],"conducted":[157],"four":[159],"publicly":[160],"available":[161],"datasets,":[163],"A2D":[165],"Sentences,":[166,168],"J-HMDB":[167],"Ref-DAVIS,":[169],"Ref-YoutubeVOS.":[171],"Performance":[172],"comparison":[173],"shows":[174],"that":[175],"achieves":[179],"state-of-the-art":[180],"performance":[181],"point-supervised":[184],"box-supervised":[186],"settings.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}