{"id":"https://openalex.org/W2951748488","doi":"https://doi.org/10.1145/3323873.3325019","title":"Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention","display_name":"Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention","publication_year":2019,"publication_date":"2019-06-05","ids":{"openalex":"https://openalex.org/W2951748488","doi":"https://doi.org/10.1145/3323873.3325019","mag":"2951748488"},"language":"en","primary_location":{"id":"doi:10.1145/3323873.3325019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323873.3325019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007360513","display_name":"Bin Jiang","orcid":"https://orcid.org/0000-0002-5840-9664"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Jiang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753382","display_name":"Xin Huang","orcid":"https://orcid.org/0000-0002-9733-6242"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Huang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604018","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-8774-8115"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7901-8793"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["The State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"The State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007360513"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":6.4334,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.97293107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8067649602890015},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6381328105926514},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5622776746749878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.545463502407074},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5029658675193787},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49791932106018066},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4824962615966797},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43722620606422424},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.435837984085083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33038830757141113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067649602890015},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6381328105926514},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5622776746749878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545463502407074},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5029658675193787},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49791932106018066},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4824962615966797},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43722620606422424},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.435837984085083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33038830757141113},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3323873.3325019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323873.3325019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G5702945905","display_name":null,"funder_award_id":"61702176","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":47,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1942126453","https://openalex.org/W1997173465","https://openalex.org/W2067766814","https://openalex.org/W2086842362","https://openalex.org/W2096479579","https://openalex.org/W2111078031","https://openalex.org/W2123024445","https://openalex.org/W2123442489","https://openalex.org/W2149557440","https://openalex.org/W2167851108","https://openalex.org/W2190406907","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2461621749","https://openalex.org/W2472970127","https://openalex.org/W2474516730","https://openalex.org/W2490414731","https://openalex.org/W2519328139","https://openalex.org/W2597958930","https://openalex.org/W2605350416","https://openalex.org/W2626473670","https://openalex.org/W2741313002","https://openalex.org/W2761419673","https://openalex.org/W2765757915","https://openalex.org/W2766402183","https://openalex.org/W2767109396","https://openalex.org/W2788362011","https://openalex.org/W2798354744","https://openalex.org/W2798538558","https://openalex.org/W2895845501","https://openalex.org/W2897628926","https://openalex.org/W2950726992","https://openalex.org/W2951590222","https://openalex.org/W2952186347","https://openalex.org/W2953106684","https://openalex.org/W2962795934","https://openalex.org/W2963017553","https://openalex.org/W2963323306","https://openalex.org/W2963341956","https://openalex.org/W2963576560","https://openalex.org/W2964089981","https://openalex.org/W2964214371","https://openalex.org/W3100481960","https://openalex.org/W4301312111","https://openalex.org/W6678470764"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1991139010"],"abstract_inverted_index":{"Given":[0],"an":[1],"untrimmed":[2],"video":[3,19],"and":[4,58,78,149,154,167],"a":[5,53,123],"description":[6],"query,":[7],"temporal":[8,15],"moment":[9,134],"retrieval":[10],"aims":[11],"to":[12,62,80,106,128,178],"localize":[13],"the":[14,18,23,34,38,48,64,69,81,87,98,108,115,130,145,152,157,160,171],"segment":[16],"within":[17],"that":[20],"best":[21],"describes":[22],"textual":[24],"query.":[25,161],"Existing":[26],"studies":[27],"predominantly":[28],"employ":[29],"coarse":[30],"frame-level":[31],"features":[32,77,85,89,102],"as":[33,176],"visual":[35],"representation,":[36],"obfuscating":[37],"specific":[39],"details":[40],"which":[41],"may":[42],"provide":[43],"critical":[44],"cues":[45],"for":[46,56],"localizing":[47],"desired":[49],"moment.":[50],"We":[51],"propose":[52],"SLTA":[54,70],"(short":[55],"\"Spatial":[57],"Language-Temporal":[59],"Attention\")":[60],"method":[61,71],"address":[63],"detail":[65],"missing":[66],"issue.":[67],"Specifically,":[68],"takes":[72],"advantage":[73],"of":[74,100,173],"object-level":[75],"local":[76,84,88,101],"attends":[79],"most":[82,146],"relevant":[83,147],"(e.g.,":[86,114],"\"girl\",":[90],"\"cup\")":[91],"by":[92],"spatial":[93],"attention.":[94],"Then":[95],"we":[96],"encode":[97],"sequence":[99],"on":[103,133,164],"consecutive":[104],"frames":[105],"capture":[107],"interaction":[109,116],"information":[110],"among":[111],"these":[112,119],"objects":[113,148],"\"pour\"":[117],"involving":[118],"two":[120,140],"objects).":[121],"Meanwhile,":[122],"language-temporal":[124],"attention":[125,141],"is":[126],"utilized":[127],"emphasize":[129],"keywords":[131,158],"based":[132],"context":[135],"information.":[136],"Therefore,":[137],"our":[138,174],"proposed":[139],"sub-networks":[142],"can":[143],"recognize":[144],"interactions":[150],"in":[151,159],"video,":[153],"simultaneously":[155],"highlight":[156],"Extensive":[162],"experiments":[163],"TACOS,":[165],"Charades-STA":[166],"DiDeMo":[168],"datasets":[169],"demonstrate":[170],"effectiveness":[172],"model":[175],"compared":[177],"state-of-the-art":[179],"methods.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}