{"id":"https://openalex.org/W4415536591","doi":"https://doi.org/10.1145/3746027.3758179","title":"Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval","display_name":"Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536591","doi":"https://doi.org/10.1145/3746027.3758179"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.01615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083888610","display_name":"Xiang Fang","orcid":"https://orcid.org/0000-0003-3231-5771"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiang Fang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3231-5771","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113067511","display_name":"Wanlong Fang","orcid":"https://orcid.org/0000-0003-4480-3107"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wanlong Fang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4480-3107","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8106-9768","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"12509","last_page":"12518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6193000078201294},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6116999983787537},{"id":"https://openalex.org/keywords/turing","display_name":"Turing","score":0.5532000064849854},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027999997138977},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6193000078201294},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C9870796","wikidata":"https://www.wikidata.org/wiki/Q490481","display_name":"Turing","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3758179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.01615","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.01615","pdf_url":"https://arxiv.org/pdf/2606.01615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2606.01615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.01615","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.01615","pdf_url":"https://arxiv.org/pdf/2606.01615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415536591.pdf","grobid_xml":"https://content.openalex.org/works/W4415536591.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1980661496","https://openalex.org/W2890502146","https://openalex.org/W2896457183","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3096609285","https://openalex.org/W3118235158","https://openalex.org/W3192973254","https://openalex.org/W4237997615","https://openalex.org/W4283456165","https://openalex.org/W4286910084","https://openalex.org/W4304080820","https://openalex.org/W4313016775","https://openalex.org/W4313476522","https://openalex.org/W4320008746","https://openalex.org/W4386075849","https://openalex.org/W4389520066","https://openalex.org/W4389520490","https://openalex.org/W4390092215","https://openalex.org/W4391341369","https://openalex.org/W4392617605","https://openalex.org/W4392903826","https://openalex.org/W4395470960","https://openalex.org/W4402753940","https://openalex.org/W4403420600","https://openalex.org/W4403791639","https://openalex.org/W4404654827","https://openalex.org/W4405395349","https://openalex.org/W4409366529","https://openalex.org/W4409370076","https://openalex.org/W4409761042","https://openalex.org/W4413145977","https://openalex.org/W4413146335","https://openalex.org/W4413155334"],"related_works":[],"abstract_inverted_index":{"Video-language":[0],"models":[1],"are":[2,102],"pivotal":[3],"for":[4,179,223,233,242],"tasks":[5],"such":[6],"as":[7,72,104],"moment":[8,180],"retrieval":[9,181],"and":[10,27,52,111,136,146,166,176,182,194,249,254],"highlight":[11],"detection,":[12],"yet":[13],"they":[14],"often":[15],"struggle":[16],"to":[17,40,49,95,118,161,197,210],"capture":[18,96],"the":[19,43,79,122,199],"dynamic,":[20],"non-linear":[21,105],"interactions":[22,101],"between":[23,46,252],"temporal":[24,97],"video":[25,90,135,217,244],"sequences":[26],"textual":[28],"semantics.":[29],"Existing":[30],"approaches,":[31],"relying":[32],"on":[33,78],"static":[34],"cross-attention":[35],"or":[36],"prompt-tuning":[37],"mechanisms,":[38],"fail":[39],"adaptively":[41],"model":[42],"evolving":[44],"relationships":[45],"modalities,":[47],"leading":[48],"suboptimal":[50],"alignment":[51,71],"limited":[53],"generalization.":[54],"Inspired":[55],"by":[56,85,140],"systems":[57,192,255],"biology,":[58],"we":[59,126],"propose":[60],"Reaction-Diffusion":[61],"Multimodal":[62],"Fusion":[63],"(RDMF),":[64],"a":[65,73,128,187,220],"novel":[66],"framework":[67,153],"that":[68,107,133],"reimagines":[69],"video-language":[70,224],"reaction-diffusion":[74],"(RD)":[75],"process,":[76],"drawing":[77],"principles":[80],"of":[81,144,201],"pattern":[82,164],"formation":[83],"introduced":[84],"Alan":[86],"Turing.":[87],"In":[88],"RDMF,":[89],"features":[91,110],"diffuse":[92],"across":[93],"time":[94],"context,":[98],"while":[99],"text-video":[100],"modeled":[103],"reactions":[106],"amplify":[108],"relevant":[109],"suppress":[112],"noise,":[113],"forming":[114],"emergent":[115],"patterns":[116],"akin":[117],"biological":[119],"systems.":[120],"Leveraging":[121],"Gray-Scott":[123],"RD":[124],"model,":[125],"design":[127],"computationally":[129],"efficient":[130],"fusion":[131],"module":[132],"integrates":[134],"text":[137],"representations,":[138],"supported":[139],"rigorous":[141],"mathematical":[142,159],"analysis":[143],"stability":[145],"convergence":[147],"using":[148],"Turing":[149],"instability":[150],"criteria.":[151],"Our":[152],"is":[154,167],"theoretically":[155],"grounded,":[156],"employing":[157],"advanced":[158],"tools":[160],"ensure":[162],"stable":[163],"formation,":[165],"practically":[168],"viable,":[169],"incorporating":[170],"standard":[171],"components":[172],"like":[173],"pretrained":[174],"encoders":[175],"DETR-style":[177],"heads":[178],"saliency":[183],"prediction.":[184],"RDMF":[185,230],"represents":[186],"pioneering":[188],"interdisciplinary":[189],"approach,":[190],"bridging":[191],"biology":[193,256],"multimedia":[195,253],"research":[196],"address":[198],"limitations":[200],"conventional":[202],"multimodal":[203],"fusion.":[204],"Preliminary":[205],"experiments":[206],"demonstrate":[207],"its":[208,227],"potential":[209],"outperform":[211],"existing":[212],"methods":[213],"in":[214,238],"identifying":[215],"salient":[216],"moments,":[218],"offering":[219],"new":[221],"paradigm":[222],"tasks.":[225],"Beyond":[226],"immediate":[228],"applications,":[229],"opens":[231],"avenues":[232],"exploring":[234],"biologically":[235],"inspired":[236],"architectures":[237],"multimedia,":[239],"with":[240],"implications":[241],"real-time":[243],"analysis,":[245],"interactive":[246],"media":[247],"systems,":[248],"cross-disciplinary":[250],"collaboration":[251],"communities.":[257]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}