{"id":"https://openalex.org/W4406903228","doi":"https://doi.org/10.1145/3715137","title":"Spatio-Temporal Attention for Text-Video Retrieval","display_name":"Spatio-Temporal Attention for Text-Video Retrieval","publication_year":2025,"publication_date":"2025-01-28","ids":{"openalex":"https://openalex.org/W4406903228","doi":"https://doi.org/10.1145/3715137"},"language":"en","primary_location":{"id":"doi:10.1145/3715137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715137","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5002748588","display_name":"Leqi Shen","orcid":"https://orcid.org/0000-0002-7742-9142"},"institutions":[{"id":"https://openalex.org/I4210115644","display_name":"Chinese Institute for Brain Research","ror":"https://ror.org/029819q61","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210115644"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leqi Shen","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China and Zhuoxi Institute of Brain and Intelligence, Hangzhou, China","School of Software and BNRist, Tsinghua University, China and Hangzhou Zhuoxi Institute of Brain and Intelligence, China"],"raw_orcid":"https://orcid.org/0000-0002-7742-9142","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China and Zhuoxi Institute of Brain and Intelligence, Hangzhou, China","institution_ids":["https://openalex.org/I4210115644"]},{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, China and Hangzhou Zhuoxi Institute of Brain and Intelligence, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051149140","display_name":"Sicheng Zhao","orcid":"https://orcid.org/0000-0001-5843-6411"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China","BNRist, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-5843-6411","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifeng Zhang","orcid":"https://orcid.org/0009-0000-5023-9288"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Zhang","raw_affiliation_strings":["JD.com Inc, Beijing, China","JD.com, China"],"raw_orcid":"https://orcid.org/0009-0000-5023-9288","affiliations":[{"raw_affiliation_string":"JD.com Inc, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD.com, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054904119","display_name":"Pengzhang Liu","orcid":"https://orcid.org/0000-0002-6031-5245"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengzhang Liu","raw_affiliation_strings":["JD.com Inc, Beijing, China","JD.com, China"],"raw_orcid":"https://orcid.org/0000-0002-6031-5245","affiliations":[{"raw_affiliation_string":"JD.com Inc, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD.com, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033318669","display_name":"Yongjun Bao","orcid":"https://orcid.org/0000-0002-7816-0587"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Bao","raw_affiliation_strings":["JD.com Inc, Beijing, China","JD.com, China"],"raw_orcid":"https://orcid.org/0000-0002-7816-0587","affiliations":[{"raw_affiliation_string":"JD.com Inc, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD.com, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057732142","display_name":"Guiguang Ding","orcid":"https://orcid.org/0000-0003-0137-9975"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiguang Ding","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China","School of Software and BNRist, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-0137-9975","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86792676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"11","first_page":"1","last_page":"20"},"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":0.9986000061035156,"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":0.9966999888420105,"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":0.9058146476745605},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.45896458625793457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44012707471847534},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.436871200799942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9058146476745605},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.45896458625793457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44012707471847534},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.436871200799942}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715137","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2186222003","https://openalex.org/W2425121537","https://openalex.org/W2602753196","https://openalex.org/W3028831795","https://openalex.org/W3155230099","https://openalex.org/W3184735396","https://openalex.org/W3186684928","https://openalex.org/W4212848270","https://openalex.org/W4214819138","https://openalex.org/W4236965008","https://openalex.org/W4244356620","https://openalex.org/W4283384437","https://openalex.org/W4283688199","https://openalex.org/W4285606530","https://openalex.org/W4296151206","https://openalex.org/W4309804076","https://openalex.org/W4312383651","https://openalex.org/W4365800005","https://openalex.org/W4367311140","https://openalex.org/W4391791458","https://openalex.org/W4400905856"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2333966947","https://openalex.org/W2399947890","https://openalex.org/W655728004","https://openalex.org/W2046272293"],"abstract_inverted_index":{"Text-video":[0],"retrieval,":[1,91],"a":[2,43,48,53,56,60],"fundamental":[3],"task":[4],"for":[5,89],"associating":[6],"textual":[7,96],"descriptions":[8],"with":[9],"video":[10,18,34,75,103,108,115,138,165],"content,":[11],"has":[12],"become":[13],"increasingly":[14],"important":[15],"in":[16,172],"the":[17,25,30,73,79,101,113,118,127,134,142,154,161,176,179,183,187,212],"domain.":[19],"Most":[20],"existing":[21],"methods":[22],"focus":[23,71,99],"on":[24,72,100,199],"single-modality":[26],"features":[27,76,109],"only":[28],"considering":[29],"knowledge":[31],"within":[32,52,66,121,137],"individual":[33],"or":[35],"text":[36,44],"modalities,":[37],"often":[38],"neglecting":[39],"cross-modal":[40],"interactions.":[41],"However,":[42],"description":[45],"corresponds":[46],"to":[47,77,98,132,146,159,174],"specific":[49],"spatio-temporal":[50,102,189],"content":[51,190],"video,":[54],"involving":[55],"certain":[57],"segment":[58],"of":[59],"frame":[61],"sequence":[62],"and":[63,117,194,205],"distinct":[64],"sub-regions":[65],"these":[67,122],"frames.":[68,123,139,166,181],"Therefore,":[69],"we":[70,85,125,152],"text-conditioned":[74,107],"bridge":[78],"modality":[80],"gap.":[81],"In":[82],"this":[83],"article,":[84],"propose":[86,126,153],"Spatio-Temporal":[87],"Attention":[88],"video-text":[90],"termed":[92],"STAttn,":[93],"which":[94],"utilizes":[95],"information":[97,136],"content.":[104],"Our":[105],"final":[106],"are":[110],"generated":[111],"from":[112,191],"text-related":[114,119,143,180,188],"frames":[116],"regions":[120],"First,":[124],"Spatial":[128],"Text-Attention":[129,156],"Module":[130,157],"(STAM)":[131],"learn":[133,160,186],"spatial":[135],"STAM":[140],"introduces":[141],"salient":[144],"patches":[145],"capture":[147],"more":[148],"fine-grained":[149],"details.":[150],"Second,":[151],"Temporal":[155,167],"(TTAM)":[158],"temporal":[162],"relationships":[163],"between":[164],"Triplet":[168],"loss":[169],"is":[170],"proposed":[171],"TTAM":[173],"enhance":[175],"attention":[177],"toward":[178],"Thus,":[182],"two":[184],"modules":[185],"both":[192],"intra-frame":[193],"inter-frame":[195],"aspects.":[196],"Extensive":[197],"experiments":[198],"three":[200],"benchmark":[201],"datasets,":[202],"MSRVTT,":[203],"ActivityNet,":[204],"DiDeMo,":[206],"demonstrate":[207],"that":[208],"our":[209],"STAttn":[210],"outperforms":[211],"state-of-the-art":[213],"methods.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
