{"id":"https://openalex.org/W7138069869","doi":"https://doi.org/10.1609/aaai.v40i12.38014","title":"T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates","display_name":"T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138069869","doi":"https://doi.org/10.1609/aaai.v40i12.38014"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.38014","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38014","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i12.38014","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124097207","display_name":"Zhitao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhitao Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747081","display_name":"Hengyu Man","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyu Man","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129654204","display_name":"Wenrui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670191","display_name":"Xingtao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingtao Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735017","display_name":"Xiaopeng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Harbin Institute of Technology\nPeng Cheng Laboratory\nHarbin Institute of Technology Suzhou Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology\nPeng Cheng Laboratory\nHarbin Institute of Technology Suzhou Research Institute","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129752001","display_name":"Debin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Debin Zhao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124097207"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33333333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"10430","last_page":"10438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8952000141143799,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8952000141143799,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12290","display_name":"Human Motion and Animation","score":0.013199999928474426,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5537999868392944},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5113999843597412},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5055999755859375},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.49630001187324524},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46950000524520874},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38280001282691956},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656000018119812},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5113999843597412},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5055999755859375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.36730000376701355},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.34450000524520874},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.38014","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38014","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.38014","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38014","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,133],"video":[3,15,160,190],"generation":[4],"techniques":[5],"have":[6],"given":[7],"rise":[8],"to":[9,50,57,136],"an":[10],"emerging":[11],"paradigm":[12],"of":[13,147,188],"generative":[14,25,148,189],"coding":[16,191],"for":[17,184],"Ultra-Low":[18],"Bitrate":[19],"(ULB)":[20],"scenarios":[21],"by":[22,33,119,193],"leveraging":[23],"powerful":[24],"priors.":[26],"However,":[27],"most":[28],"existing":[29,178],"methods":[30],"are":[31],"limited":[32],"domain":[34],"specificity":[35],"(e.g.,":[36],"facial":[37],"or":[38,41,59],"human":[39],"videos)":[40],"excessive":[42],"dependence":[43],"on":[44,103],"high-level":[45,83],"text":[46],"guidance,":[47],"which":[48],"tend":[49],"inadequately":[51],"capture":[52],"fine-grained":[53],"motion":[54,80,91,97,140,175,195],"details,":[55],"leading":[56],"unrealistic":[58],"incoherent":[60],"reconstructions.":[61],"To":[62],"address":[63],"these":[64],"challenges,":[65],"we":[66,127],"propose":[67],"Trajectory-Guided":[68],"Generative":[69],"Video":[70],"Coding":[71],"(dubbed":[72],"T-GVC),":[73],"a":[74,88,129,185],"novel":[75,186],"framework":[76,171],"that":[77,94,153,169],"bridges":[78],"low-level":[79],"tracking":[81],"with":[82],"semantic":[84,105,115],"understanding.":[85],"T-GVC":[86,154],"features":[87],"semantic-aware":[89],"sparse":[90,99],"sampling":[92],"pipeline":[93],"extracts":[95],"pixel-wise":[96],"as":[98],"trajectory":[100],"points":[101],"based":[102],"their":[104],"importance,":[106],"significantly":[107],"reducing":[108],"the":[109,144,182],"bitrate":[110],"while":[111],"preserving":[112],"critical":[113],"temporal":[114],"information.":[116],"In":[117],"addition,":[118],"integrating":[120],"trajectory-aligned":[121],"loss":[122],"constraints":[123],"into":[124],"diffusion":[125],"processes,":[126],"introduce":[128],"training-free":[130],"guidance":[131],"mechanism":[132],"latent":[134],"space":[135],"ensure":[137],"physically":[138],"plausible":[139],"patterns":[141],"without":[142],"sacrificing":[143],"inherent":[145],"capabilities":[146],"models.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"outperforms":[155],"both":[156],"traditional":[157],"and":[158],"neural":[159],"codecs":[161],"under":[162],"ULB":[163],"conditions.":[164],"Furthermore,":[165],"additional":[166],"experiments":[167],"confirm":[168],"our":[170],"achieves":[172],"more":[173],"precise":[174],"control":[176],"than":[177],"text-guided":[179],"methods,":[180],"paving":[181],"way":[183],"direction":[187],"guided":[192],"geometric":[194],"modeling.":[196]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}