{"id":"https://openalex.org/W7167912287","doi":"https://doi.org/10.1145/3805712.3809742","title":"Generation-Augmented Video Corpus Moment Retrieval","display_name":"Generation-Augmented Video Corpus Moment Retrieval","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167912287","doi":"https://doi.org/10.1145/3805712.3809742"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809742","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809742","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136695439","display_name":"Mingjin Kuai","orcid":null},"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":"Mingjin Kuai","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-0230-4595","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140423158","display_name":"Qianyin Xiao","orcid":"https://orcid.org/0009-0007-8189-8279"},"institutions":[{"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":"Qianyin Xiao","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-8189-8279","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015420479","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0003-2258-1291"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2258-1291","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140403304","display_name":"Jin Peng","orcid":"https://orcid.org/0009-0008-2401-1931"},"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":"Jin Peng","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-2401-1931","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081165986","display_name":"Lizi Liao","orcid":"https://orcid.org/0000-0002-9973-3305"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lizi Liao","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9973-3305","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","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"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"857","last_page":"868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9833999872207642,"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":0.9833999872207642,"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":0.004999999888241291,"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/T10028","display_name":"Topic Modeling","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/discriminative-model","display_name":"Discriminative model","score":0.6980999708175659},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6391000151634216},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5403000116348267},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5297999978065491},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5157999992370605},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.48500001430511475},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118000030517578},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6980999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633999943733215},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809742","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809742","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7466752529144287,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2194775991","https://openalex.org/W2808399042","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2964089981","https://openalex.org/W2975813532","https://openalex.org/W2998355566","https://openalex.org/W3021397474","https://openalex.org/W3043840704","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3155721152","https://openalex.org/W3176182290","https://openalex.org/W3200217958","https://openalex.org/W3207454933","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4304142044","https://openalex.org/W4310390842","https://openalex.org/W4384028531","https://openalex.org/W4385565351","https://openalex.org/W4385571847","https://openalex.org/W4385573866","https://openalex.org/W4386766790","https://openalex.org/W4389523905","https://openalex.org/W4389890968","https://openalex.org/W4392172801","https://openalex.org/W4397026222","https://openalex.org/W4399435757","https://openalex.org/W4400525588","https://openalex.org/W4402704596","https://openalex.org/W4406370386","https://openalex.org/W4406457620","https://openalex.org/W4408326921","https://openalex.org/W4408351886","https://openalex.org/W4409366186","https://openalex.org/W4409366588","https://openalex.org/W4409367202","https://openalex.org/W4411472307","https://openalex.org/W4412377027","https://openalex.org/W4412377351","https://openalex.org/W4413144971","https://openalex.org/W4413145061","https://openalex.org/W4413147612","https://openalex.org/W4413156834","https://openalex.org/W4414197672","https://openalex.org/W4414198468","https://openalex.org/W4415796023","https://openalex.org/W4415797115","https://openalex.org/W4415797872","https://openalex.org/W7117320526","https://openalex.org/W7133208784","https://openalex.org/W7160098069","https://openalex.org/W7160185874"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Corpus":[1],"Moment":[2],"Retrieval":[3],"(VCMR)":[4],"requires":[5],"models":[6,103],"to":[7,16,41,65,129,139],"efficiently":[8],"retrieve":[9],"and":[10,167],"precisely":[11],"locate":[12],"specific":[13],"moments":[14],"relevant":[15],"natural":[17],"language":[18],"queries":[19],"within":[20],"a":[21,53,93,115,121,126,145],"massive,":[22],"untrimmed":[23],"video":[24],"corpus.":[25],"However,":[26],"existing":[27],"discriminative":[28],"approaches":[29],"typically":[30],"rely":[31],"on":[32,110,157],"shallow":[33],"visual-textual":[34],"feature":[35],"matching":[36,64],"mechanisms,":[37],"which":[38,120],"often":[39],"struggle":[40],"capture":[42],"fine-grained":[43,141],"semantic":[44,77,127],"differences.":[45],"To":[46,85],"address":[47],"this":[48],"limitation,":[49],"we":[50,91,113,143],"propose":[51,144],"Video-GAR,":[52],"novel":[54],"framework":[55],"that":[56,69,96,149,162],"reframes":[57],"the":[58,70,87,98],"conventional":[59],"retrieval":[60,166],"task":[61],"from":[62],"superficial":[63],"generative":[66],"understanding,":[67],"positing":[68],"capability":[71],"for":[72,104],"query":[73],"reconstruction":[74],"evidences":[75],"deep":[76],"comprehension.":[78],"Specifically,":[79],"Video-GAR":[80,163],"orchestrates":[81],"three":[82],"synergistic":[83],"components:":[84],"overcome":[86],"computational":[88],"efficiency":[89],"bottleneck,":[90],"construct":[92],"Bi-Mamba":[94],"backbone":[95],"leverages":[97],"linear":[99],"complexity":[100],"of":[101],"state-space":[102],"efficient":[105],"global":[106],"context":[107],"modeling.":[108],"Building":[109],"these":[111],"representations,":[112],"introduce":[114],"generation-augmented":[116],"fusion":[117],"module,":[118],"in":[119],"training-only":[122],"decoder":[123],"acts":[124],"as":[125],"regularizer":[128],"implicitly":[130],"calibrate":[131],"cross-modal":[132],"attention":[133],"without":[134],"increasing":[135],"inference":[136,173],"overhead.":[137],"Finally,":[138],"ensure":[140],"precision,":[142],"boundary-aware":[146],"localization":[147,168],"strategy":[148],"integrates":[150],"boundary":[151],"modeling":[152],"with":[153],"categorical":[154],"supervision.":[155],"Experiments":[156],"two":[158],"benchmark":[159],"datasets":[160],"demonstrate":[161],"significantly":[164],"improves":[165],"accuracy":[169],"while":[170],"maintaining":[171],"outstanding":[172],"speed.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}