{"id":"https://openalex.org/W4401386916","doi":"https://doi.org/10.1109/tcsvt.2024.3439692","title":"Future Feature-Based Supervised Contrastive Learning for Streaming Perception","display_name":"Future Feature-Based Supervised Contrastive Learning for Streaming Perception","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401386916","doi":"https://doi.org/10.1109/tcsvt.2024.3439692"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3439692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439692","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/A5029082445","display_name":"Tongbo Wang","orcid":"https://orcid.org/0000-0003-2113-3681"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tongbo Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022334521","display_name":"Hua Huang","orcid":"https://orcid.org/0000-0003-2587-1702"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Huang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029082445"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72403528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":"12","first_page":"13611","last_page":"13625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9805999994277954,"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/T10057","display_name":"Face and Expression Recognition","score":0.9805999994277954,"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":0.9745000004768372,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9442999958992004,"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":0.7532694339752197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6331989765167236},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5797503590583801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48623552918434143},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4856356680393219},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4478326439857483},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4285314083099365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34522104263305664},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32761284708976746},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08549323678016663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532694339752197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331989765167236},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5797503590583801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48623552918434143},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4856356680393219},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4478326439857483},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4285314083099365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34522104263305664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32761284708976746},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08549323678016663},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3439692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439692","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W2097324787","https://openalex.org/W2570343428","https://openalex.org/W2799058067","https://openalex.org/W2842511635","https://openalex.org/W2950697717","https://openalex.org/W2955189650","https://openalex.org/W2963026686","https://openalex.org/W2963037989","https://openalex.org/W2963350250","https://openalex.org/W2963351448","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W2995484963","https://openalex.org/W3010594275","https://openalex.org/W3018757597","https://openalex.org/W3018902719","https://openalex.org/W3034467781","https://openalex.org/W3084874594","https://openalex.org/W3092900809","https://openalex.org/W3093047473","https://openalex.org/W3108457314","https://openalex.org/W3108655343","https://openalex.org/W3109870774","https://openalex.org/W3127131334","https://openalex.org/W3134517928","https://openalex.org/W3134867831","https://openalex.org/W3136761610","https://openalex.org/W3155107193","https://openalex.org/W3164543136","https://openalex.org/W3174156594","https://openalex.org/W3188394685","https://openalex.org/W3204023867","https://openalex.org/W4212912983","https://openalex.org/W4221166276","https://openalex.org/W4226056010","https://openalex.org/W4283317841","https://openalex.org/W4283795993","https://openalex.org/W4285203457","https://openalex.org/W4289527857","https://openalex.org/W4293428377","https://openalex.org/W4312500310","https://openalex.org/W4317795300","https://openalex.org/W4318821268","https://openalex.org/W4372269209","https://openalex.org/W4387543539","https://openalex.org/W4390547596","https://openalex.org/W6750227808","https://openalex.org/W6761178061","https://openalex.org/W6766548695","https://openalex.org/W6776700526","https://openalex.org/W6798838024","https://openalex.org/W6810974023","https://openalex.org/W6853321581","https://openalex.org/W6859823517"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W2905271011","https://openalex.org/W2793270624","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W4298151006","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Streaming":[0],"perception,":[1,218],"a":[2,53,83,125,146,198],"critical":[3],"task":[4],"in":[5,92,100,115,191,201],"computer":[6],"vision,":[7],"involves":[8],"the":[9,87,101,109,121,132,153,202,214,220],"real-time":[10],"prediction":[11,114,228],"of":[12,36,89,111,135,155,173,204,216],"object":[13,91,112,227],"locations":[14],"within":[15,229],"video":[16,230],"sequences":[17],"based":[18,140],"on":[19,29,141,180],"prior":[20],"frames.":[21,170],"While":[22],"current":[23,93],"methods":[24,190],"like":[25],"StreamYOLO":[26],"mainly":[27],"rely":[28],"coordinate":[30],"information,":[31],"they":[32],"often":[33],"fall":[34],"short":[35],"delivering":[37],"precise":[38],"predictions":[39],"due":[40],"to":[41,64,151],"feature":[42,147],"misalignment":[43],"between":[44,86],"input":[45],"data":[46],"and":[47,75,94,97,137,145,209,225],"supervisory":[48],"labels.":[49],"In":[50,119],"this":[51,66],"paper,":[52],"novel":[54],"method,":[55],"Future":[56],"Feature-based":[57],"Supervised":[58],"Contrastive":[59],"Learning":[60],"(FFSCL),":[61],"is":[62,175],"introduced":[63],"address":[65],"challenge":[67],"by":[68,159],"incorporating":[69],"appearance":[70,88,161],"features":[71,162],"from":[72,163,168],"future":[73,142,164,210],"frames":[74,96,165],"leveraging":[76],"supervised":[77,156,205],"contrastive":[78,157,206],"learning":[79,158,207],"techniques.":[80],"FFSCL":[81,122,174,186],"establishes":[82],"robust":[84],"correspondence":[85],"an":[90],"past":[95,169],"its":[98],"location":[99],"subsequent":[102],"frame.":[103],"This":[104,195],"integrated":[105],"method":[106,123],"significantly":[107],"improves":[108],"accuracy":[110],"position":[113],"streaming":[116,192,217],"perception":[117,193],"tasks.":[118,194],"addition,":[120],"includes":[124],"sample":[126],"pair":[127],"construction":[128],"module":[129],"(SPC)":[130],"for":[131,222],"efficient":[133,226],"creation":[134],"positive":[136],"negative":[138],"samples":[139],"frame":[143,211],"labels":[144],"consistency":[148],"loss":[149],"(FCL)":[150],"enhance":[152],"effectiveness":[154],"linking":[160],"with":[166],"those":[167],"The":[171],"efficacy":[172],"demonstrated":[176],"through":[177],"extensive":[178],"experiments":[179],"two":[181],"large-scale":[182],"benchmark":[183],"datasets,":[184],"where":[185],"consistently":[187],"outperforms":[188],"state-of-the-art":[189],"study":[196],"represents":[197],"significant":[199],"advancement":[200],"incorporation":[203],"techniques":[208],"information":[212],"into":[213],"realm":[215],"paving":[219],"way":[221],"more":[223],"accurate":[224],"streams.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}