{"id":"https://openalex.org/W3088744711","doi":"https://doi.org/10.1109/tmm.2021.3063631","title":"Frame-Wise Cross-Modal Matching for Video Moment Retrieval","display_name":"Frame-Wise Cross-Modal Matching for Video Moment Retrieval","publication_year":2021,"publication_date":"2021-03-10","ids":{"openalex":"https://openalex.org/W3088744711","doi":"https://doi.org/10.1109/tmm.2021.3063631","mag":"3088744711"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3063631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3063631","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.10434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haoyu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Tang","raw_affiliation_strings":["School of Software Engineering, Xi’an Jiaotong University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi’an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["School of Software Engineering, Xi’an Jiaotong University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0002-3081-8781","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi’an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5764","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zan Gao","orcid":"https://orcid.org/0000-0003-2182-5741"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zan Gao","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-2182-5741","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyong Cheng","orcid":"https://orcid.org/0000-0003-1109-5028"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Cheng","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-1109-5028","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9766,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.94959885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"24","issue":null,"first_page":"1338","last_page":"1349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9337999820709229,"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":0.9337999820709229,"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":0.04039999842643738,"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/T11439","display_name":"Video Analysis and Summarization","score":0.009700000286102295,"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/moment","display_name":"Moment (physics)","score":0.5651999711990356},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4648999869823456},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4088999927043915},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.40639999508857727},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.39559999108314514},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.36739999055862427},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.866100013256073},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.40639999508857727},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.39559999108314514},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2021.3063631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3063631","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2009.10434","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.10434","pdf_url":"https://arxiv.org/pdf/2009.10434","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:2009.10434","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.10434","pdf_url":"https://arxiv.org/pdf/2009.10434","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/G3648701118","display_name":null,"funder_award_id":"61902223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7696304900","display_name":null,"funder_award_id":"62006142","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W262578090","https://openalex.org/W1522734439","https://openalex.org/W1942126453","https://openalex.org/W2086842362","https://openalex.org/W2131774270","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2472970127","https://openalex.org/W2597958930","https://openalex.org/W2604113307","https://openalex.org/W2739107216","https://openalex.org/W2741313002","https://openalex.org/W2753311918","https://openalex.org/W2788362011","https://openalex.org/W2798354744","https://openalex.org/W2808399042","https://openalex.org/W2884293275","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2895240652","https://openalex.org/W2897628926","https://openalex.org/W2904824998","https://openalex.org/W2951748488","https://openalex.org/W2953461088","https://openalex.org/W2962677524","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963095467","https://openalex.org/W2963247196","https://openalex.org/W2963393391","https://openalex.org/W2963542836","https://openalex.org/W2963662190","https://openalex.org/W2963735856","https://openalex.org/W2964089981","https://openalex.org/W2970898753","https://openalex.org/W2974212192","https://openalex.org/W2975813532","https://openalex.org/W2981750465","https://openalex.org/W2997762001","https://openalex.org/W2998495542","https://openalex.org/W2998712570","https://openalex.org/W3004413500","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3035640828","https://openalex.org/W6629028937","https://openalex.org/W6678224444","https://openalex.org/W6749876669","https://openalex.org/W6761268011","https://openalex.org/W6761423549"],"related_works":[],"abstract_inverted_index":{"Video":[0],"moment":[1,8,42,124],"retrieval":[2],"targets":[3],"at":[4],"retrieving":[5],"a":[6,10,13,140,156],"golden":[7,110],"in":[9,43,101,264,305],"video":[11,46,58,75,131,149,192,248],"for":[12,144,164,245],"given":[14],"natural":[15],"language":[16],"query.":[17],"The":[18],"main":[19],"challenges":[20],"of":[21,28,108,285,302],"this":[22,174,195],"task":[23],"include":[24],"1)":[25],"the":[26,32,36,40,51,67,84,105,109,114,122,127,145,160,185,189,208,261,265,270,283,300],"requirement":[27,128],"accurately":[29],"localizing":[30],"(i.e.,":[31],"start":[33],"time":[34,38],"and":[35,48,57,78,95,148,153,191,280],"end":[37],"of)":[39],"relevant":[41,88,123,247],"an":[44,199,213,221,256],"untrimmed":[45],"stream,":[47],"2)":[49],"bridging":[50],"semantic":[52,236],"gap":[53],"between":[54,188,216],"textual":[55],"query":[56,85,147,190,232],"contents.":[59,249],"To":[60,112],"tackle":[61],"those":[62,179],"problems,":[63],"early":[64],"approaches":[65],"adopt":[66],"sliding":[68],"window":[69],"or":[70],"uniform":[71],"sampling":[72],"to":[73,86,98,104,119,129,138,226,231,241,259,268,298],"collect":[74],"clips":[76,132],"first":[77],"then":[79,154],"match":[80],"each":[81],"clip":[82],"with":[83,234],"identify":[87],"clips.":[89],"Obviously,":[90],"these":[91],"strategies":[92],"are":[93,239],"time-consuming":[94],"often":[96],"lead":[97],"unsatisfied":[99],"accuracy":[100],"localization":[102,271],"due":[103],"unpredictable":[106],"length":[107],"moment.":[111],"avoid":[113],"limitations,":[115],"researchers":[116],"recently":[117],"attempt":[118],"directly":[120],"predict":[121],"boundaries":[125,210],"without":[126],"generate":[130,139],"first.":[133],"One":[134],"mainstream":[135],"approach":[136,158],"is":[137,224,252],"multimodal":[141,161],"feature":[142,162],"vector":[143,163],"target":[146],"frames":[150,263],"(e.g.,":[151],"concatenation)":[152],"use":[155],"regression":[157],"upon":[159],"boundary":[165],"detection.":[166],"Although":[167],"some":[168],"progress":[169],"has":[170],"been":[171,295],"achieved":[172],"by":[173],"approach,":[175],"we":[176,197,254],"argue":[177],"that":[178,253],"methods":[180],"have":[181,294],"not":[182],"well":[183],"captured":[184],"cross-modal":[186],"interactions":[187],"frames.":[193],"In":[194,219],"paper,":[196],"propose":[198,255],"Attentive":[200],"Cross-modal":[201],"Relevance":[202],"Matching":[203],"(ACRM)":[204],"model":[205,266],"which":[206,238],"predicts":[207],"temporal":[209],"based":[211],"on":[212,275],"interaction":[214],"modeling":[215],"two":[217,276],"modalities.":[218],"addition,":[220],"attention":[222],"module":[223],"introduced":[225],"automatically":[227],"assign":[228],"higher":[229],"weights":[230],"words":[233],"richer":[235],"cues,":[237],"considered":[240],"be":[242],"more":[243],"important":[244],"finding":[246],"Another":[250],"contribution":[251],"additional":[257],"predictor":[258],"utilize":[260],"internal":[262],"training":[267],"improve":[269],"accuracy.":[272],"Extensive":[273],"experiments":[274],"public":[277],"datasets":[278],"TACoS":[279],"Charades-STA":[281],"demonstrate":[282],"superiority":[284],"our":[286,306],"method":[287],"over":[288],"several":[289],"state-of-the-art":[290],"methods.":[291],"Ablation":[292],"studies":[293],"also":[296],"conducted":[297],"examine":[299],"effectiveness":[301],"different":[303],"modules":[304],"ACRM":[307],"model.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2020-10-01T00:00:00"}