{"id":"https://openalex.org/W4400032968","doi":"https://doi.org/10.1109/tcsvt.2024.3419119","title":"Temporally Consistent Referring Video Object Segmentation With Hybrid Memory","display_name":"Temporally Consistent Referring Video Object Segmentation With Hybrid Memory","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400032968","doi":"https://doi.org/10.1109/tcsvt.2024.3419119"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3419119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3419119","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://admin.research-repository.uwa.edu.au/en/publications/daff14b4-b75c-463c-8971-7785a27182d9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039119622","display_name":"Bo Miao","orcid":"https://orcid.org/0000-0002-3025-4429"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bo Miao","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3025-4429","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071549690","display_name":"Yongsheng Gao","orcid":"https://orcid.org/0000-0002-5382-5351"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yongsheng Gao","raw_affiliation_strings":["School of Engineering, Griffith University, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5382-5351","affiliations":[{"raw_affiliation_string":"School of Engineering, Griffith University, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215307","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0002-8216-1128"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8216-1128","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5206-3842","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039119622"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":3.9133,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94736714,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"11","first_page":"11373","last_page":"11385"},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.995199978351593,"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":0.989799976348877,"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":0.6734186410903931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6663597822189331},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6588832139968872},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5947873592376709},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.542949914932251},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5211731791496277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3651161789894104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734186410903931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6663597822189331},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6588832139968872},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5947873592376709},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.542949914932251},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5211731791496277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3651161789894104}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tcsvt.2024.3419119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3419119","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/daff14b4-b75c-463c-8971-7785a27182d9","is_oa":true,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/daff14b4-b75c-463c-8971-7785a27182d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Miao, B, Bennamoun, M, Gao, Y, Shah, M & Mian, A 2024, 'Temporally Consistent Referring Video Object Segmentation with Hybrid Memory', IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 11, 10572009, pp. 11373-11385. https://doi.org/10.1109/TCSVT.2024.3419119","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/431861","is_oa":true,"landing_page_url":"https://hdl.handle.net/10072/431861","pdf_url":"https://research-repository.griffith.edu.au/bitstreams/dd757678-f1ea-4ca1-ad2a-894e0d227d79/download","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"},{"id":"pmh:oai:pure.atira.dk:publications/daff14b4-b75c-463c-8971-7785a27182d9","is_oa":true,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/daff14b4-b75c-463c-8971-7785a27182d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Miao , B , Bennamoun , M , Gao , Y , Shah , M &amp; Mian , A 2024 , ' Temporally Consistent Referring Video Object Segmentation with Hybrid Memory ' , IEEE Transactions on Circuits and Systems for Video Technology , vol. 34 , no. 11 , 10572009 , pp. 11373-11385 . https://doi.org/10.1109/TCSVT.2024.3419119","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/daff14b4-b75c-463c-8971-7785a27182d9","is_oa":true,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/daff14b4-b75c-463c-8971-7785a27182d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Miao, B, Bennamoun, M, Gao, Y, Shah, M & Mian, A 2024, 'Temporally Consistent Referring Video Object Segmentation with Hybrid Memory', IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 11, 10572009, pp. 11373-11385. https://doi.org/10.1109/TCSVT.2024.3419119","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3091033834","display_name":null,"funder_award_id":"IH180100002","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G3206439402","display_name":null,"funder_award_id":"FT210100268","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G8222488688","display_name":null,"funder_award_id":"FT210100268","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W2034014085","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2294182682","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2564998703","https://openalex.org/W2565639579","https://openalex.org/W2740667773","https://openalex.org/W2787091153","https://openalex.org/W2799157347","https://openalex.org/W2799239273","https://openalex.org/W2916797271","https://openalex.org/W2954890601","https://openalex.org/W2962766617","https://openalex.org/W2962825871","https://openalex.org/W2962942822","https://openalex.org/W2963109634","https://openalex.org/W2963253279","https://openalex.org/W2963351448","https://openalex.org/W2963354481","https://openalex.org/W2964218467","https://openalex.org/W2964343881","https://openalex.org/W2965373594","https://openalex.org/W2965729941","https://openalex.org/W2967622921","https://openalex.org/W2980088508","https://openalex.org/W2983693499","https://openalex.org/W2986050084","https://openalex.org/W2989161706","https://openalex.org/W2990205821","https://openalex.org/W2990806702","https://openalex.org/W2995633856","https://openalex.org/W2996881884","https://openalex.org/W3005248472","https://openalex.org/W3034328552","https://openalex.org/W3034438741","https://openalex.org/W3034538699","https://openalex.org/W3035042565","https://openalex.org/W3038429043","https://openalex.org/W3045477169","https://openalex.org/W3094664776","https://openalex.org/W3104844437","https://openalex.org/W3106546328","https://openalex.org/W3108819577","https://openalex.org/W3132520841","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3170630188","https://openalex.org/W3171516518","https://openalex.org/W3177322837","https://openalex.org/W3178075329","https://openalex.org/W3183673520","https://openalex.org/W3186378100","https://openalex.org/W3188132485","https://openalex.org/W3192692200","https://openalex.org/W3212940248","https://openalex.org/W3215899623","https://openalex.org/W4200631531","https://openalex.org/W4200631575","https://openalex.org/W4226024706","https://openalex.org/W4283796148","https://openalex.org/W4289752563","https://openalex.org/W4304084115","https://openalex.org/W4307504011","https://openalex.org/W4312396403","https://openalex.org/W4312438304","https://openalex.org/W4312560592","https://openalex.org/W4312690830","https://openalex.org/W4312734171","https://openalex.org/W4312981390","https://openalex.org/W4313054169","https://openalex.org/W4319978663","https://openalex.org/W4361983876","https://openalex.org/W4377235251","https://openalex.org/W4379928661","https://openalex.org/W4379984073","https://openalex.org/W4385245566","https://openalex.org/W4385252655","https://openalex.org/W4386065815","https://openalex.org/W4387350728","https://openalex.org/W4387448157","https://openalex.org/W4390872515","https://openalex.org/W4390872868","https://openalex.org/W4390872914","https://openalex.org/W4390873204","https://openalex.org/W4390873614","https://openalex.org/W4390874496","https://openalex.org/W4393305204","https://openalex.org/W4402727770","https://openalex.org/W6639406879","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6784094891","https://openalex.org/W6784713722","https://openalex.org/W6785496661","https://openalex.org/W6792105337","https://openalex.org/W6796280812","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6809716307","https://openalex.org/W6846581650","https://openalex.org/W6853447796","https://openalex.org/W6867518200","https://openalex.org/W6881022228"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W2898210368","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referring":[0],"Video":[1],"Object":[2],"Segmentation":[3],"(R-VOS)":[4],"methods":[5],"face":[6],"challenges":[7],"in":[8],"maintaining":[9],"consistent":[10,82],"object":[11],"segmentation":[12],"due":[13],"to":[14,70,79,94,116],"temporal":[15,35,97,109],"context":[16],"variability":[17],"and":[18,57,126],"the":[19,39,72,96],"presence":[20],"of":[21,60,99],"other":[22],"visually":[23],"similar":[24],"objects.":[25],"We":[26],"propose":[27,86],"an":[28],"end-to-end":[29],"R-VOS":[30,121],"paradigm":[31],"that":[32,49,105],"explicitly":[33],"models":[34],"instance":[36],"consistency":[37,98,110],"alongside":[38],"referring":[40],"segmentation.":[41,101],"Specifically,":[42],"we":[43,85],"introduce":[44],"a":[45,87,112],"novel":[46],"hybrid":[47],"memory":[48],"facilitates":[50],"inter-frame":[51],"collaboration":[52],"for":[53],"robust":[54],"spatio-temporal":[55],"matching":[56],"propagation.":[58],"Features":[59],"frames":[61,74],"with":[62],"automatically":[63],"generated":[64],"high-quality":[65],"reference":[66],"masks":[67],"are":[68],"propagated":[69],"segment":[71],"remaining":[73],"based":[75],"on":[76,119],"multi-granularity":[77],"association":[78],"achieve":[80],"temporally":[81],"R-VOS.":[83],"Furthermore,":[84],"new":[88],"Mask":[89],"Consistency":[90],"Score":[91],"(MCS)":[92],"metric":[93],"evaluate":[95],"video":[100],"Extensive":[102],"experiments":[103],"demonstrate":[104],"our":[106],"approach":[107],"enhances":[108],"by":[111],"significant":[113],"margin,":[114],"leading":[115],"top-ranked":[117],"performance":[118],"popular":[120],"benchmarks,":[122],"i.e.,":[123],"Ref-YouTube-VOS":[124],"(67.1%)":[125],"Ref-DAVIS17":[127],"(65.6%).":[128],"The":[129],"code":[130],"is":[131],"available":[132],"at":[133],"<uri":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/bo-miao/HTR</uri>.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
