{"id":"https://openalex.org/W4403780507","doi":"https://doi.org/10.1145/3664647.3680673","title":"T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval","display_name":"T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780507","doi":"https://doi.org/10.1145/3664647.3680673"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680673","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058019221","display_name":"Yili Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yili Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672021","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0002-3966-511X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066465215","display_name":"Keke Gai","orcid":"https://orcid.org/0000-0001-6784-0221"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Gai","raw_affiliation_strings":["School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056033969","display_name":"Bang Liu","orcid":"https://orcid.org/0000-0002-9483-8984"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bang Liu","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al & Mila, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al & Mila, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601598","display_name":"Gang Xiong","orcid":"https://orcid.org/0000-0002-3190-6521"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Xiong","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Australia Institute of Machine Learning, University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"Australia Institute of Machine Learning, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058019221"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.9971,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77803464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3955","last_page":"3963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9972000122070312,"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":0.7785463929176331},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.658255934715271},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5143057107925415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4585937559604645},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4301193058490753},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35420095920562744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785463929176331},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.658255934715271},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5143057107925415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4585937559604645},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4301193058490753},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35420095920562744}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680673","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.11432","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11432","pdf_url":"https://arxiv.org/pdf/2408.11432","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":"doi:10.1145/3664647.3680673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680673","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2897439619","https://openalex.org/W2917888609","https://openalex.org/W2963017553","https://openalex.org/W3035265375","https://openalex.org/W3168640669","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4319049530","https://openalex.org/W4385569809","https://openalex.org/W4386072365"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W2399947890","https://openalex.org/W655728004","https://openalex.org/W2046272293"],"abstract_inverted_index":{"Current":[0],"text-video":[1],"retrieval":[2,24,78,83,118,153,172,177],"methods":[3],"mainly":[4],"rely":[5],"on":[6,159,179],"cross-modal":[7],"matching":[8,30],"between":[9,31],"queries":[10],"and":[11,35,45,62,65,106,133,186],"videos":[12,109,139],"to":[13,22,116,137,174],"calculate":[14],"their":[15,74,145],"similarity":[16],"scores,":[17],"which":[18,96],"are":[19,56],"then":[20],"sorted":[21],"obtain":[23],"results.":[25],"This":[26],"method":[27,149],"considers":[28],"the":[29,36,50,152,170],"each":[32],"candidate":[33,108],"video":[34,92,104,130],"query,":[37],"but":[38,73],"it":[39],"incurs":[40],"a":[41,90,98],"significant":[42],"time":[43,112,119,173],"cost":[44],"will":[46],"increase":[47,51],"notably":[48],"with":[49,110,166],"of":[52,155,169],"candidates.":[53],"Generative":[54],"models":[55,158],"common":[57],"in":[58,70,76,85],"natural":[59],"language":[60],"processing":[61],"computer":[63],"vision,":[64],"have":[66],"been":[67],"successfully":[68],"applied":[69],"document":[71],"retrieval,":[72],"application":[75],"multimodal":[77],"remains":[79],"unexplored.":[80],"To":[81,124],"enhance":[82],"efficiency,":[84],"this":[86,126],"paper,":[87],"we":[88,128],"introduce":[89],"model-based":[91],"indexer":[93],"named":[94],"T2VIndexer,":[95],"is":[97,191],"sequence-to-sequence":[99],"generative":[100],"model":[101],"directly":[102],"generating":[103],"identifiers":[105],"retrieving":[107],"constant":[111],"complexity.":[113],"T2VIndexer":[114],"aims":[115],"reduce":[117],"while":[120,143],"maintaining":[121],"high":[122],"accuracy.":[123],"achieve":[125,175],"goal,":[127],"propose":[129],"identifier":[131],"encoding":[132],"query-identifier":[134],"augmentation":[135],"approaches":[136],"represent":[138],"as":[140],"short":[141],"sequences":[142],"preserving":[144],"semantic":[146],"information.":[147],"Our":[148],"consistently":[150],"enhances":[151],"efficiency":[154],"current":[156],"state-of-the-art":[157],"four":[160],"standard":[161],"datasets.":[162],"It":[163],"enables":[164],"baselines":[165],"only":[167],"30%-50%":[168],"original":[171],"better":[176],"performance":[178],"MSR-VTT":[180],"(+1.0%),":[181],"MSVD":[182],"(+1.8%),":[183],"ActivityNet":[184],"(+1.5%),":[185],"DiDeMo":[187],"(+0.2%).":[188],"The":[189],"code":[190],"available":[192],"at":[193],"https://github.com/Lilidamowang/T2VIndexer-generativeSearch.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}