{"id":"https://openalex.org/W3155721152","doi":"https://doi.org/10.1145/3404835.3462874","title":"Video Corpus Moment Retrieval with Contrastive Learning","display_name":"Video Corpus Moment Retrieval with Contrastive Learning","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155721152","doi":"https://doi.org/10.1145/3404835.3462874","mag":"3155721152"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462874","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.06247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Zhang","orcid":null},"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":true,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aixin Sun","orcid":null},"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":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Jing","raw_affiliation_strings":["Agency for Science, Technology and Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guoshun Nan","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guoshun Nan","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liangli Zhen","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liangli Zhen","raw_affiliation_strings":["Agency for Science, Technology and Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joey Tianyi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joey Tianyi Zhou","raw_affiliation_strings":["Agency for Science, Technology and Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rick Siow Mong Goh","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Agency for Science, Technology and Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":4.3695,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.9560349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"685","last_page":"695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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/encode","display_name":"ENCODE","score":0.6256999969482422},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5508000254631042},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5422000288963318},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4690000116825104},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.3815999925136566},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6256999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5508000254631042},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.491100013256073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3404835.3462874","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.06247","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.06247","pdf_url":"https://arxiv.org/pdf/2105.06247","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.06247","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.06247","pdf_url":"https://arxiv.org/pdf/2105.06247","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":[{"id":"https://openalex.org/G5791238452","display_name":null,"funder_award_id":"A18A1b0045 and A18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1573040851","https://openalex.org/W2108598243","https://openalex.org/W2138621090","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2740747242","https://openalex.org/W2798991696","https://openalex.org/W2808399042","https://openalex.org/W2889185481","https://openalex.org/W2890502146","https://openalex.org/W2891456603","https://openalex.org/W2897439619","https://openalex.org/W2897628926","https://openalex.org/W2904824998","https://openalex.org/W2948958195","https://openalex.org/W2962677524","https://openalex.org/W2963095467","https://openalex.org/W2963524571","https://openalex.org/W2964089981","https://openalex.org/W2964232540","https://openalex.org/W2964345792","https://openalex.org/W2970231061","https://openalex.org/W2970401629","https://openalex.org/W2975813532","https://openalex.org/W2981750465","https://openalex.org/W2997762001","https://openalex.org/W2998355566","https://openalex.org/W2998388430","https://openalex.org/W2998495542","https://openalex.org/W2998712570","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3035265375","https://openalex.org/W3035339529","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3035640828","https://openalex.org/W3043840704","https://openalex.org/W3093051565","https://openalex.org/W3093154363","https://openalex.org/W3095206982","https://openalex.org/W6600106792","https://openalex.org/W6600704668"],"related_works":[],"abstract_inverted_index":{"Given":[0],"a":[1,16,20,23,29,103,180],"collection":[2],"of":[3,22],"untrimmed":[4],"and":[5,35,67,105,119,129,135,157,190],"unsegmented":[6],"videos,":[7],"video":[8,34,127,134,146,159,191],"corpus":[9],"moment":[10,18,171],"retrieval":[11,89,196],"(VCMR)":[12],"is":[13,94,150,198],"to":[14,28,48,52,69,74,87,125,132,151,168,174],"retrieve":[15],"temporal":[17],"(i.e.,":[19],"fraction":[21],"video)":[24],"that":[25],"semantically":[26],"corresponds":[27,173],"given":[30],"text":[31,36,130,136,189],"query.":[32],"As":[33],"are":[37,44],"from":[38],"two":[39,45,61,121],"distinct":[40],"feature":[41],"spaces,":[42],"there":[43],"general":[46],"approaches":[47],"address":[49],"VCMR:":[50],"(i)":[51],"separately":[53,138,192],"encode":[54],"each":[55],"modality":[56,62],"representations,":[57],"then":[58],"align":[59],"the":[60,82,91,116,170,175],"representations":[63,77,137],"for":[64,78,112,143,193],"query":[65,79,156,176],"processing,":[66],"(ii)":[68],"adopt":[70,115],"fine-grained":[71],"cross-modal":[72,203],"interaction":[73,204],"learn":[75,133],"multi-modal":[76],"processing.":[80],"While":[81],"second":[83],"approach":[84,93,118],"often":[85],"leads":[86],"better":[88,141],"accuracy,":[90],"first":[92,117],"far":[95],"more":[96],"efficient.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101],"propose":[102],"Retrieval":[104],"Localization":[106],"Network":[107],"with":[108,140,200],"Contrastive":[109],"Learning":[110],"(ReLoCLNet)":[111],"VCMR.":[113,144],"We":[114],"introduce":[120],"contrastive":[122,147,164],"learning":[123,148,165],"objectives":[124],"refine":[126],"encoder":[128,131],"but":[139],"alignment":[142],"The":[145,162],"(VideoCL)":[149],"maximize":[152],"mutual":[153],"information":[154],"between":[155],"candidate":[158],"at":[160,177],"video-level.":[161],"frame":[163],"(FrameCL)":[166],"aims":[167],"highlight":[169],"region":[172],"frame-level,":[178],"within":[179],"video.":[181],"Experimental":[182],"results":[183],"show":[184],"that,":[185],"although":[186],"ReLoCLNet":[187],"encodes":[188],"efficiency,":[194],"its":[195],"accuracy":[197],"comparable":[199],"baselines":[201],"adopting":[202],"learning.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":11}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-04-26T00:00:00"}