{"id":"https://openalex.org/W2894280539","doi":"https://doi.org/10.1609/aaai.v33i01.33019062","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","display_name":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2894280539","doi":"https://doi.org/10.1609/aaai.v33i01.33019062","mag":"2894280539"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019062","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019062","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4938/4811","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4938/4811","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101404512","display_name":"Huijuan Xu","orcid":"https://orcid.org/0000-0002-4778-5584"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huijuan Xu","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101939666","display_name":"Kun He","orcid":"https://orcid.org/0000-0002-0828-0794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun He","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061227594","display_name":"Bryan A. Plummer","orcid":"https://orcid.org/0000-0002-7074-3219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan A. Plummer","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053011888","display_name":"Leonid Sigal","orcid":"https://orcid.org/0000-0002-3942-2804"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Leonid Sigal","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042663603","display_name":"Stan Sclaroff","orcid":"https://orcid.org/0000-0002-0711-4313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stan Sclaroff","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":332,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"9062","last_page":"9069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9977999925613403,"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":0.9952999949455261,"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":0.8394830226898193},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7274830341339111},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.6760188341140747},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6302454471588135},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5888957977294922},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5780474543571472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5768287777900696},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5493879914283752},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49349772930145264},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4646702706813812},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4390484690666199},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40615516901016235},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37209492921829224},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12240606546401978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394830226898193},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7274830341339111},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.6760188341140747},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6302454471588135},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5888957977294922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5780474543571472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5768287777900696},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5493879914283752},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49349772930145264},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4646702706813812},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4390484690666199},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40615516901016235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37209492921829224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12240606546401978},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019062","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019062","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4938/4811","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4938","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019062","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019062","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4938/4811","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2894280539.pdf","grobid_xml":"https://content.openalex.org/works/W2894280539.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1714639292","https://openalex.org/W1895577753","https://openalex.org/W1916445035","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2016053056","https://openalex.org/W2102705755","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2153579005","https://openalex.org/W2171810632","https://openalex.org/W2172888184","https://openalex.org/W2179022885","https://openalex.org/W2254252455","https://openalex.org/W2255577267","https://openalex.org/W2293453011","https://openalex.org/W2337252826","https://openalex.org/W2346425926","https://openalex.org/W2394849137","https://openalex.org/W2461621749","https://openalex.org/W2463565445","https://openalex.org/W2508429489","https://openalex.org/W2563296158","https://openalex.org/W2565656701","https://openalex.org/W2604730366","https://openalex.org/W2606473278","https://openalex.org/W2611788449","https://openalex.org/W2613718673","https://openalex.org/W2727849499","https://openalex.org/W2745461083","https://openalex.org/W2788713610","https://openalex.org/W2952686080","https://openalex.org/W2963191264","https://openalex.org/W2963247196","https://openalex.org/W2963321993","https://openalex.org/W2963656855","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W2963775347","https://openalex.org/W2963916161","https://openalex.org/W2963954913","https://openalex.org/W2964089981","https://openalex.org/W2964214371","https://openalex.org/W3098232790","https://openalex.org/W3099206234","https://openalex.org/W3100481960","https://openalex.org/W4292516920","https://openalex.org/W4294170691","https://openalex.org/W4294576248","https://openalex.org/W4299341000","https://openalex.org/W4299801216","https://openalex.org/W4300123490","https://openalex.org/W4300785486","https://openalex.org/W4394661212","https://openalex.org/W6635091486","https://openalex.org/W6638791942","https://openalex.org/W6639657675","https://openalex.org/W6680375555","https://openalex.org/W6690386867","https://openalex.org/W6731356633","https://openalex.org/W6737009557","https://openalex.org/W6742324346","https://openalex.org/W6785234230","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2395860100","https://openalex.org/W2036154621","https://openalex.org/W795077857","https://openalex.org/W2074513378","https://openalex.org/W2376416463","https://openalex.org/W2007338512","https://openalex.org/W2491583298","https://openalex.org/W2969725083"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,29,95,101],"problem":[3],"of":[4,97],"text-based":[5],"activity":[6],"retrieval":[7],"in":[8,33,104],"video.":[9,26],"Given":[10],"a":[11,40,83,105],"sentence":[12],"describing":[13],"an":[14,24,120],"activity,":[15],"our":[16],"task":[17],"is":[18,112],"to":[19,67,81,93],"retrieve":[20],"matching":[21],"clips":[22,71],"from":[23],"untrimmed":[25],"To":[27],"capture":[28],"inherent":[30],"structures":[31],"present":[32],"both":[34],"text":[35,59],"and":[36,46,50,72,77,134],"video,":[37],"we":[38,57,89],"introduce":[39],"multilevel":[41],"model":[42],"that":[43],"integrates":[44],"vision":[45],"language":[47],"features":[48,60,92],"earlier":[49],"more":[51],"tightly":[52],"than":[53],"prior":[54,127],"work.":[55],"First,":[56],"inject":[58],"early":[61],"on":[62,129],"when":[63],"generating":[64],"clip":[65],"proposals,":[66],"help":[68],"eliminate":[69],"unlikely":[70],"thus":[73],"speed":[74],"up":[75],"processing":[76,96],"boost":[78],"performance.":[79],"Second,":[80],"learn":[82],"fine-grained":[84],"similarity":[85],"metric":[86],"for":[87],"retrieval,":[88],"use":[90],"visual":[91],"modulate":[94],"query":[98,117],"sentences":[99],"at":[100],"word":[102],"level":[103],"recurrent":[106],"neural":[107],"network.":[108],"A":[109],"multi-task":[110],"loss":[111],"also":[113],"employed":[114],"by":[115],"adding":[116],"re-generation":[118],"as":[119],"auxiliary":[121],"task.":[122],"Our":[123],"approach":[124],"significantly":[125],"outperforms":[126],"work":[128],"two":[130],"challenging":[131],"benchmarks:":[132],"Charades-STA":[133],"ActivityNet":[135],"Captions.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":90},{"year":2020,"cited_by_count":53},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}