{"id":"https://openalex.org/W3173223111","doi":"https://doi.org/10.1109/tmm.2021.3090595","title":"Spatial-Temporal Graphs for Cross-Modal Text2Video Retrieval","display_name":"Spatial-Temporal Graphs for Cross-Modal Text2Video Retrieval","publication_year":2021,"publication_date":"2021-06-23","ids":{"openalex":"https://openalex.org/W3173223111","doi":"https://doi.org/10.1109/tmm.2021.3090595","mag":"3173223111"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3090595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3090595","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":["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/A5101422759","display_name":"Xue Song","orcid":"https://orcid.org/0000-0003-0324-277X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xue Song","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0324-277X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3148-264X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101422759"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":6.401,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.97558063,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"24","issue":null,"first_page":"2914","last_page":"2923"},"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":0.9980999827384949,"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":0.9972000122070312,"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":0.8638653755187988},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6421061754226685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.514011025428772},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46583428978919983},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4554821848869324},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4504002332687378},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4408961534500122},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43769627809524536},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43755242228507996},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4195508658885956},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21153372526168823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638653755187988},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6421061754226685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.514011025428772},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46583428978919983},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4554821848869324},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4504002332687378},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4408961534500122},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43769627809524536},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43755242228507996},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4195508658885956},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21153372526168823},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3090595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3090595","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2086842362","https://openalex.org/W2137275576","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2284126738","https://openalex.org/W2425121537","https://openalex.org/W2526286384","https://openalex.org/W2530794863","https://openalex.org/W2565656701","https://openalex.org/W2725249286","https://openalex.org/W2750526644","https://openalex.org/W2753311918","https://openalex.org/W2774267535","https://openalex.org/W2806331055","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2886970679","https://openalex.org/W2890531016","https://openalex.org/W2897152025","https://openalex.org/W2914699769","https://openalex.org/W2941765879","https://openalex.org/W2945809413","https://openalex.org/W2962934715","https://openalex.org/W2963076818","https://openalex.org/W2963165299","https://openalex.org/W2963441581","https://openalex.org/W2963514444","https://openalex.org/W2963735856","https://openalex.org/W2964081303","https://openalex.org/W2975813532","https://openalex.org/W2984008963","https://openalex.org/W3004319625","https://openalex.org/W3034882096","https://openalex.org/W3035265375","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3102887392","https://openalex.org/W3204588463","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6677265961","https://openalex.org/W6726873649","https://openalex.org/W6727649915","https://openalex.org/W6728495041","https://openalex.org/W6746260573","https://openalex.org/W6747225742","https://openalex.org/W6752110883","https://openalex.org/W6784184991"],"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/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2039176012"],"abstract_inverted_index":{"Cross-modal":[0],"text":[1,12,35,49],"to":[2,6,23,28,139,145,163,178,186,197,203],"video":[3,33,72,123,166],"retrieval":[4,115],"aims":[5],"find":[7],"relevant":[8,65],"videos":[9,66,92,132],"for":[10,17,97,168,206],"given":[11],"queries,":[13],"which":[14,110],"is":[15,27,176,195],"crucial":[16],"various":[18],"real-world":[19],"applications.":[20],"The":[21],"key":[22],"address":[24],"this":[25,125],"task":[26],"build":[29],"the":[30,38,48,64,75,82,87,98,105,119,146,151,154,165,180,188,200,204,212,215],"correspondence":[31],"between":[32,84,148,191],"and":[34,54,103,142,218,226],"such":[36],"that":[37,130],"related":[39],"samples":[40],"from":[41],"different":[42],"modalities":[43],"can":[44,160],"be":[45,161],"aligned.":[46],"As":[47],"(sentence)":[50],"contains":[51],"both":[52,224],"nouns":[53],"verbs":[55],"representing":[56],"objects":[57,141],"as":[58,60,133],"well":[59],"their":[61],"interactions,":[62,109],"retrieving":[63],"requires":[67],"a":[68,128],"fine-grained":[69],"understanding":[70],"of":[71,100,107,121,214],"contents---not":[73],"only":[74],"semantic":[76],"concepts":[77],"(i.e.,":[78],"objects)":[79],"but":[80],"also":[81],"interactions":[83,156,190],"them.":[85],"Nevertheless,":[86],"current":[88],"approaches":[89],"mostly":[90],"represent":[91],"with":[93],"aggregated":[94],"frame-level":[95],"features":[96],"learning":[99],"joint":[101,169],"space":[102,170],"ignore":[104],"information":[106],"object":[108,155],"usually":[111],"results":[112],"in":[113,157],"suboptimal":[114],"performance.":[116],"To":[117],"improve":[118],"performance":[120],"cross-modal":[122,207],"retrieval,":[124],"paper":[126],"proposes":[127],"framework":[129,217],"models":[131],"spatial-temporal":[134,152,183,189],"graphs":[135],"where":[136],"nodes":[137],"correspond":[138,144],"visual":[140],"edges":[143],"relations/interactions":[147],"objects.":[149],"With":[150],"graphs,":[153,184],"frame":[158],"sequences":[159],"captured":[162],"enrich":[164],"representations":[167,181],"learning.":[171],"Specifically,":[172],"Graph":[173],"Convolutional":[174],"Network":[175],"introduced":[177,196],"learn":[179],"on":[182,223],"aiming":[185],"encode":[187,199],"objects;":[192],"while":[193],"BERT":[194],"dynamically":[198],"sentence":[201],"according":[202],"context":[205],"retrieval.":[208],"Extensive":[209],"experiments":[210],"verify":[211],"effectiveness":[213],"proposed":[216],"it":[219],"achieves":[220],"promising":[221],"performances":[222],"MSR-VTT":[225],"LSMDC":[227],"datasets.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}