{"id":"https://openalex.org/W7224818152","doi":"https://doi.org/10.48550/arxiv.2610.39322","title":"MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion","display_name":"MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224818152","doi":"https://doi.org/10.48550/arxiv.2610.39322"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39322","pdf_url":"https://arxiv.org/pdf/2610.39322","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087023638","display_name":"Meiqi Gong","orcid":"https://orcid.org/0000-0001-6039-5268","observed_orcids":["https://orcid.org/0000-0001-6039-5268"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong, Meiqi","raw_affiliation_strings":["Electronic Information School Wuhan University Wuhan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information School Wuhan University Wuhan , China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160210255","display_name":"Hao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":["Electronic Information School Wuhan University Wuhan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information School Wuhan University Wuhan , China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160226579","display_name":"Jiayi Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Jiayi","raw_affiliation_strings":["School of Robotics Wuhan University Wuhan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Robotics Wuhan University Wuhan , China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.00039999998989515007,"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/T13579","display_name":"Image and Video Stabilization","score":0.0003000000142492354,"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/long-term-memory","display_name":"long-term memory","score":0.6520000100135803},{"id":"https://openalex.org/keywords/short-term-memory","display_name":"short-term memory","score":0.7440000176429749},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.7289999723434448},{"id":"https://openalex.org/keywords/temporal-smoothing","display_name":"temporal smoothing","score":0.7429999709129333},{"id":"https://openalex.org/keywords/memory-bank","display_name":"memory bank","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478999853134155},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C172081034","wikidata":"https://www.wikidata.org/wiki/Q185961","display_name":"Time perception","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2985957978","wikidata":"https://www.wikidata.org/wiki/Q492","display_name":"Human memory","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39322","pdf_url":"https://arxiv.org/pdf/2610.39322","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39322","doi":"https://doi.org/10.48550/arxiv.2610.39322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39322","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39322","pdf_url":"https://arxiv.org/pdf/2610.39322","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000978580","display_name":null,"funder_award_id":"62676289","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224818152.pdf","grobid_xml":"https://content.openalex.org/works/W7224818152.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7077910193","https://openalex.org/W6910788811","https://openalex.org/W7223983599","https://openalex.org/W4414587280","https://openalex.org/W7128388519","https://openalex.org/W7128045588","https://openalex.org/W7162449825","https://openalex.org/W7148897016","https://openalex.org/W7203535702","https://openalex.org/W4366520378"],"abstract_inverted_index":{"Multimodal":[0],"videos":[1],"contain":[2],"rich":[3],"temporal":[4,20,36,55,76,95,130,146],"cues":[5,104],"that":[6,83,139],"can":[7,31],"facilitate":[8],"faithful":[9],"fusion.":[10],"However,":[11],"existing":[12,149],"video":[13],"fusion":[14,29,113,143,153],"methods":[15],"mainly":[16],"rely":[17],"on":[18],"short-range":[19],"interactions,":[21],"leaving":[22],"valuable":[23],"long-term":[24],"information":[25,87],"underexplored.":[26],"Moreover,":[27],"inconsistent":[28],"representations":[30],"cause":[32],"flickering":[33],"artifacts,":[34],"undermining":[35],"coherence.":[37],"To":[38,93],"address":[39],"these":[40],"coupled":[41],"challenges,":[42],"we":[43],"propose":[44],"MemoryFusion,":[45],"a":[46,70,79,89,97,120],"two-stage":[47],"framework":[48],"integrating":[49],"cross-temporal":[50],"memory":[51],"learning":[52],"with":[53,78],"progressive":[54],"refinement.":[56],"Considering":[57],"the":[58,66,111],"complementary":[59],"roles":[60],"of":[61],"adjacent":[62],"and":[63,145,151],"distant":[64],"frames,":[65],"first":[67],"stage":[68,117],"combines":[69],"Short-Term":[71],"Memory":[72,81],"Bank":[73,82],"for":[74,105],"local":[75],"guidance":[77],"Long-Term":[80],"preserves":[84],"reliable":[85],"historical":[86],"through":[88],"fusion-oriented":[90],"update":[91],"strategy.":[92],"mitigate":[94],"fluctuations,":[96],"Temporal":[98,124],"Smoothing":[99],"Module":[100,126],"leverages":[101],"soft":[102],"motion":[103],"coarse":[106],"background":[107],"stabilization.":[108],"Building":[109],"upon":[110],"resulting":[112],"prior,":[114],"The":[115,155],"second":[116],"further":[118],"employs":[119],"lightweight":[121],"3D":[122],"residual":[123],"Refinement":[125],"to":[127],"correct":[128],"remaining":[129],"inconsistencies":[131],"while":[132],"enhancing":[133],"structural":[134],"details.":[135],"Extensive":[136],"experiments":[137],"demonstrate":[138],"MemoryFusion":[140],"achieves":[141],"superior":[142],"quality":[144],"consistency":[147],"over":[148],"frame-based":[150],"video-based":[152],"methods.":[154],"source":[156],"code":[157],"is":[158],"publicly":[159],"available":[160],"at":[161],"https://github.com/Meiqi-Gong/MemoryFusion.":[162]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-10-31T00:00:00"}