{"id":"https://openalex.org/W4390044151","doi":"https://doi.org/10.1109/tcsvt.2023.3345852","title":"Unveiling the Power of Visible-Thermal Video Object Segmentation","display_name":"Unveiling the Power of Visible-Thermal Video Object Segmentation","publication_year":2023,"publication_date":"2023-12-21","ids":{"openalex":"https://openalex.org/W4390044151","doi":"https://doi.org/10.1109/tcsvt.2023.3345852"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3345852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3345852","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":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/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]},{"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","GB"],"is_corresponding":true,"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"],"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/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]},{"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","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, Coventry, U.K"],"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, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China","Tencent Youtu Lab, Shanghai, China","Shanghai Jiao Tong Universtity, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Shanghai Jiao Tong Universtity, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"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"],"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":["https://openalex.org/A5054794372"],"corresponding_institution_ids":["https://openalex.org/I3045169105","https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.614,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70863403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"34","issue":"7","first_page":"5376","last_page":"5388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9973000288009644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9954000115394592,"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":0.7902729511260986},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7290778756141663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7127602100372314},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.687034010887146},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6555694937705994},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.6289052367210388},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5736445784568787},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5390417575836182},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5186804533004761},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46929770708084106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45950812101364136},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4436781108379364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10118800401687622},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.07516279816627502},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06700137257575989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902729511260986},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7290778756141663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7127602100372314},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.687034010887146},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6555694937705994},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.6289052367210388},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5736445784568787},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5390417575836182},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5186804533004761},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46929770708084106},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45950812101364136},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4436781108379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10118800401687622},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.07516279816627502},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06700137257575989},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3345852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3345852","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2055635457","https://openalex.org/W2340671224","https://openalex.org/W2470139095","https://openalex.org/W2527415613","https://openalex.org/W2775609985","https://openalex.org/W2792215676","https://openalex.org/W2798441772","https://openalex.org/W2799157347","https://openalex.org/W2890447039","https://openalex.org/W2916743882","https://openalex.org/W2916797271","https://openalex.org/W2921749009","https://openalex.org/W2960426010","https://openalex.org/W2963131444","https://openalex.org/W2963253279","https://openalex.org/W2963548592","https://openalex.org/W2963732700","https://openalex.org/W2963905288","https://openalex.org/W2963983744","https://openalex.org/W2964343881","https://openalex.org/W2982723417","https://openalex.org/W2990205821","https://openalex.org/W2997487053","https://openalex.org/W3035295069","https://openalex.org/W3035807818","https://openalex.org/W3101990647","https://openalex.org/W3117097536","https://openalex.org/W3120735733","https://openalex.org/W3127756064","https://openalex.org/W3132520841","https://openalex.org/W3151956566","https://openalex.org/W3153607844","https://openalex.org/W3158472981","https://openalex.org/W3160550216","https://openalex.org/W3175132347","https://openalex.org/W3182236906","https://openalex.org/W3183904268","https://openalex.org/W3200949949","https://openalex.org/W3202424564","https://openalex.org/W3206439726","https://openalex.org/W4214737929","https://openalex.org/W4226083961","https://openalex.org/W4226126595","https://openalex.org/W4283808043","https://openalex.org/W4293732316","https://openalex.org/W4296913506","https://openalex.org/W4297677284","https://openalex.org/W4304098539","https://openalex.org/W4312376179","https://openalex.org/W4312396403","https://openalex.org/W4312510454","https://openalex.org/W4312612915","https://openalex.org/W4312668764","https://openalex.org/W4313007055","https://openalex.org/W4313044016","https://openalex.org/W4367000115","https://openalex.org/W4376312146","https://openalex.org/W4379984073","https://openalex.org/W4386065959","https://openalex.org/W4386076516","https://openalex.org/W4390872599","https://openalex.org/W4390873799","https://openalex.org/W6754033419","https://openalex.org/W6759534164","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6843869883","https://openalex.org/W6847228076","https://openalex.org/W6852276098","https://openalex.org/W6852629184"],"related_works":["https://openalex.org/W2392812199","https://openalex.org/W4200176076","https://openalex.org/W598185802","https://openalex.org/W2355516524","https://openalex.org/W2361471170","https://openalex.org/W2025616642","https://openalex.org/W1954972543","https://openalex.org/W2954738200","https://openalex.org/W4220843223","https://openalex.org/W4226107239"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress,":[2],"Video":[3],"Object":[4],"Segmentation":[5],"(VOS)":[6],"remains":[7],"challenging":[8,50,165],"in":[9,88,119,141,164],"complex":[10],"situations":[11],"such":[12],"as":[13,31,69],"low":[14],"light":[15,54],"and":[16,55,58,77,96,104,168,174],"dark":[17],"scenes.":[18],"In":[19],"this":[20,177],"paper,":[21],"we":[22,36,175],"tackle":[23],"the":[24,114,128,156,181],"visibility":[25],"limitations":[26],"by":[27,132],"introducing":[28],"thermal":[29,56],"information":[30],"auxillary":[32],"for":[33,42,80,98],"VOS.":[34,185],"Specifically,":[35],"generate":[37],"a":[38,64,133],"hybrid":[39],"benchmark":[40],"dataset":[41],"Visible-Thermal":[43,65],"VOS,":[44],"named":[45,68],"VisT300,":[46],"which":[47],"contains":[48],"300":[49],"videos":[51],"with":[52],"visible":[53],"frames":[57],"corresponding":[59],"object":[60,83],"mask":[61],"annotations.":[62],"Besides,":[63],"integration":[66],"Network,":[67],"VTiNet,":[70],"is":[71,86],"proposed":[72],"to":[73,160],"use":[74],"both":[75],"cross-modal":[76,93],"cross-frame":[78],"propagation":[79,97],"accurate":[81],"video":[82],"segmentation.":[84],"It":[85],"advantageous":[87],"two":[89],"aspects:":[90],"1)":[91],"effective":[92,108],"feature":[94],"fusion":[95],"strong":[99],"expressions":[100],"on":[101],"visible,":[102],"thermal,":[103],"fused":[105],"modalities;":[106],"2)":[107],"modality-sensitive":[109],"memory":[110],"bank":[111],"enables":[112],"preserving":[113],"most":[115],"valuable":[116],"historical":[117],"contexts":[118],"each":[120],"modality.":[121],"Extensive":[122],"experiments":[123],"demonstrate":[124],"our":[125],"VTiNet":[126],"outperforms":[127],"state-of-the-art":[129],"VOS":[130],"works":[131],"large":[134],"margin":[135],"(over":[136],"5%":[137],"than":[138],"RGB":[139],"SotAs":[140],"Mean":[142],"J&F).":[143],"Our":[144],"preliminary":[145],"research":[146],"clearly":[147],"recovers":[148],"that":[149],"importing":[150],"complementary":[151],"modalities":[152],"can":[153],"effectively":[154],"increase":[155],"strength":[157],"of":[158,183],"models":[159],"achieve":[161],"robust":[162],"segmentation":[163],"scenarios.":[166],"Data":[167],"code":[169],"are":[170],"released":[171],"at":[172],"https://github.com/yjybuaa/vtinet,":[173],"hope":[176],"work":[178],"will":[179],"promote":[180],"progress":[182],"visible-thermal":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}