{"id":"https://openalex.org/W4392693676","doi":"https://doi.org/10.1109/tip.2024.3374130","title":"Weakly-Supervised RGBD Video Object Segmentation","display_name":"Weakly-Supervised RGBD Video Object Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392693676","doi":"https://doi.org/10.1109/tip.2024.3374130","pmid":"https://pubmed.ncbi.nlm.nih.gov/38470575"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3374130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3374130","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5054794372","display_name":"Jinyu Yang","orcid":"https://orcid.org/0009-0006-3567-6299"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Jinyu Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","University of Birmingham, Birmingham, U.K"],"raw_orcid":"https://orcid.org/0009-0006-3567-6299","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"University of Birmingham, Birmingham, U.K","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048649183","display_name":"Mingqi Gao","orcid":"https://orcid.org/0000-0002-8688-8228"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Mingqi Gao","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","University of Warwick, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8688-8228","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"University of Warwick, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063285882","display_name":"Feng Zheng","orcid":"https://orcid.org/0000-0002-1701-9141"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1701-9141","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026486701","display_name":"Xiantong Zhen","orcid":"https://orcid.org/0000-0001-5213-0462"},"institutions":[{"id":"https://openalex.org/I4210128140","display_name":"Guangdong University of Petrochemical Technology","ror":"https://ror.org/030ffke25","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210128140"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantong Zhen","raw_affiliation_strings":["College of Computer Science, Guangdong University of Petrochemical Technology, Maoming, China"],"raw_orcid":"https://orcid.org/0000-0001-5213-0462","affiliations":[{"raw_affiliation_string":"College of Computer Science, Guangdong University of Petrochemical Technology, Maoming, China","institution_ids":["https://openalex.org/I4210128140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"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":"Rongrong Ji","raw_affiliation_strings":["Department of Artificial Intelligence, School of Informatics, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, School of Informatics, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082634513","display_name":"Ling Shao","orcid":"https://orcid.org/0000-0002-8264-6117"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Shao","raw_affiliation_strings":["UCAS-Terminus AI Laboratory, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8264-6117","affiliations":[{"raw_affiliation_string":"UCAS-Terminus AI Laboratory, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085971943","display_name":"Ale\u0161 Leonardis","orcid":"https://orcid.org/0000-0003-0773-3277"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ale\u0161 Leonardis","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0773-3277","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, U.K","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55742336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"33","issue":null,"first_page":"2158","last_page":"2170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T11605","display_name":"Visual Attention and Saliency Detection","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.7730820178985596},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7205676436424255},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6736224889755249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6694093346595764},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6693472862243652},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5250725150108337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47620901465415955},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.47103172540664673},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.41335737705230713},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2209932506084442}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7730820178985596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7205676436424255},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6736224889755249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694093346595764},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6693472862243652},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5250725150108337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47620901465415955},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.47103172540664673},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.41335737705230713},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2209932506084442}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3374130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3374130","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:38470575","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38470575","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8065005635","display_name":null,"funder_award_id":"62176068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8142145165","display_name":null,"funder_award_id":"62122035","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":64,"referenced_works":["https://openalex.org/W1495267108","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1985238052","https://openalex.org/W2031489346","https://openalex.org/W2037971948","https://openalex.org/W2067107771","https://openalex.org/W2124351162","https://openalex.org/W2151295993","https://openalex.org/W2163309385","https://openalex.org/W2168804568","https://openalex.org/W2470139095","https://openalex.org/W2533218643","https://openalex.org/W2552414813","https://openalex.org/W2555182955","https://openalex.org/W2564998703","https://openalex.org/W2568271872","https://openalex.org/W2585592883","https://openalex.org/W2751422254","https://openalex.org/W2776256943","https://openalex.org/W2792215676","https://openalex.org/W2799157347","https://openalex.org/W2889658408","https://openalex.org/W2912429050","https://openalex.org/W2917353338","https://openalex.org/W2928165649","https://openalex.org/W2963227409","https://openalex.org/W2963253279","https://openalex.org/W2963311325","https://openalex.org/W2966759264","https://openalex.org/W2990205821","https://openalex.org/W2991778094","https://openalex.org/W2998027361","https://openalex.org/W2999458807","https://openalex.org/W3008978349","https://openalex.org/W3015871565","https://openalex.org/W3034297219","https://openalex.org/W3106773277","https://openalex.org/W3109120382","https://openalex.org/W3114753236","https://openalex.org/W3117097536","https://openalex.org/W3124434019","https://openalex.org/W3127756064","https://openalex.org/W3160550216","https://openalex.org/W3163168119","https://openalex.org/W3175132347","https://openalex.org/W3182236906","https://openalex.org/W3200949949","https://openalex.org/W3209993199","https://openalex.org/W4200318028","https://openalex.org/W4214696292","https://openalex.org/W4214737929","https://openalex.org/W4220869836","https://openalex.org/W4224247218","https://openalex.org/W4230728863","https://openalex.org/W4297677284","https://openalex.org/W4312396403","https://openalex.org/W4312510454","https://openalex.org/W4313044016","https://openalex.org/W4386076516","https://openalex.org/W6776305959","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6843869883"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2124969951","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703"],"abstract_inverted_index":{"Depth":[0],"information":[1],"opens":[2],"up":[3],"new":[4,48],"opportunities":[5],"for":[6,50],"video":[7],"object":[8],"segmentation":[9],"(VOS)":[10],"to":[11,29,97,121,130,137,163],"be":[12,85],"more":[13],"accurate":[14],"and":[15,36,67,134],"robust":[16],"in":[17,62,106],"complex":[18,132],"scenes.":[19],"However,":[20],"the":[21,30,89,107,111,123,165],"RGBD":[22,34,51,168],"VOS":[23],"task":[24],"is":[25],"largely":[26],"unexplored":[27],"due":[28],"expensive":[31],"collection":[32],"of":[33,39,91,140,167],"data":[35],"time-consuming":[37],"annotation":[38],"segmentation.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"first":[45,108],"introduce":[46],"a":[47,73,101,117,126],"benchmark":[49],"VOS,":[52],"named":[53],"DepthVOS,":[54],"which":[55,83],"contains":[56],"350":[57],"videos":[58],"(over":[59],"55k":[60],"frames":[61],"total)":[63],"annotated":[64],"with":[65,100,152],"masks":[66,99],"bounding":[68,92,102],"boxes.":[69],"We":[70,156],"futher":[71],"propose":[72],"novel,":[74],"strong":[75],"baseline":[76],"model":[77,112],"-":[78],"Fused":[79],"Color-Depth":[80],"Network":[81],"(FusedCDNet),":[82],"can":[84],"trained":[86],"solely":[87],"under":[88],"supervision":[90],"boxes,":[93],"while":[94],"being":[95],"used":[96],"generate":[98],"box":[103],"guideline":[104],"only":[105],"frame.":[109],"Thereby,":[110],"possesses":[113],"three":[114],"major":[115],"advantages:":[116],"weakly-supervised":[118,135],"training":[119],"strategy":[120],"overcome":[122],"high-cost":[124],"annotation,":[125],"cross-modal":[127],"fusion":[128],"module":[129],"handle":[131],"scenes,":[133],"inference":[136],"promote":[138],"ease":[139],"use.":[141],"Extensive":[142],"experiments":[143],"demonstrate":[144],"that":[145],"our":[146,159],"proposed":[147],"method":[148],"performs":[149],"on":[150,161],"par":[151],"top":[153],"fully-supervised":[154],"algorithms.":[155],"will":[157],"open-source":[158],"project":[160],"https://github.com/yjybuaa/depthvos/":[162],"facilitate":[164],"development":[166],"VOS.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}