{"id":"https://openalex.org/W4304092331","doi":"https://doi.org/10.1145/3503161.3548010","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","display_name":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092331","doi":"https://doi.org/10.1145/3503161.3548010"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548010","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100324824","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-4622-0119"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017609606","display_name":"Di Xu","orcid":"https://orcid.org/0000-0002-1344-2495"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Xu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018276259","display_name":"Dongliang He","orcid":"https://orcid.org/0000-0002-1129-8610"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang He","raw_affiliation_strings":["Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324319","display_name":"Fu Li","orcid":"https://orcid.org/0000-0003-0319-0308"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Li","raw_affiliation_strings":["Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005367680","display_name":"Zhong Ji","orcid":"https://orcid.org/0000-0002-2197-3739"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ji","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Computer Science Department, Aberystwyth University, SY23 3FL, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Aberystwyth University, SY23 3FL, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050031109","display_name":"Errui Ding","orcid":"https://orcid.org/0000-0002-1867-5378"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Errui Ding","raw_affiliation_strings":["Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4887","last_page":"4898"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9961000084877014,"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":0.991100013256073,"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":0.8153870105743408},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6348800659179688},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5119506120681763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5092290639877319},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47228842973709106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44890257716178894},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4481198787689209},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.157316654920578},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12736228108406067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153870105743408},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6348800659179688},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5119506120681763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5092290639877319},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47228842973709106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44890257716178894},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4481198787689209},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.157316654920578},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12736228108406067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548010","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1931639407","https://openalex.org/W2187089797","https://openalex.org/W2425121537","https://openalex.org/W2552161745","https://openalex.org/W2604314403","https://openalex.org/W2739770654","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2963017553","https://openalex.org/W2963672682","https://openalex.org/W2964018924","https://openalex.org/W2989322838","https://openalex.org/W2997326970","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3043840704","https://openalex.org/W3107973541","https://openalex.org/W3108864070","https://openalex.org/W3145807616","https://openalex.org/W3153005511","https://openalex.org/W3175939205","https://openalex.org/W3180463990","https://openalex.org/W3201519611","https://openalex.org/W3204588463","https://openalex.org/W3207042189","https://openalex.org/W3207460436","https://openalex.org/W4225414521","https://openalex.org/W4247924304"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W6643695","https://openalex.org/W4381248170","https://openalex.org/W2817971408","https://openalex.org/W3189621521"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1],"(VTR)":[2],"is":[3,124],"an":[4,107],"attractive":[5],"yet":[6],"challenging":[7],"task":[8],"for":[9,16,66,102,132],"multi-modal":[10],"understanding,":[11],"which":[12,68],"aims":[13],"to":[14,32,112,126,153,174],"search":[15],"relevant":[17],"video":[18,34,121],"(text)":[19],"given":[20],"a":[21,59,119],"query":[22],"(video).":[23],"Existing":[24],"methods":[25,203],"typically":[26],"employ":[27],"completely":[28],"heterogeneous":[29],"visual-textual":[30],"information":[31,45],"align":[33],"and":[35,88,98,146,161,180,211],"text,":[36],"whilst":[37],"lacking":[38],"the":[39,70,81,133,138,150,154,164,176,189,198],"awareness":[40],"of":[41,84,191],"homogeneous":[42],"high-level":[43,76,86,115,129,156,182,193],"semantic":[44,109],"residing":[46],"in":[47,54],"both":[48,159],"modalities.":[49],"To":[50],"fill":[51],"this":[52,55],"gap,":[53],"work,":[56],"we":[57,79,105,136],"propose":[58],"novel":[60],"visual-linguistic":[61],"aligning":[62],"model":[63,123],"named":[64],"HiSE":[65],"VTR,":[67],"improves":[69],"cross-modal":[71],"representation":[72],"by":[73],"incorporating":[74],"explicit":[75,85,192],"semantics.":[77,100,116,130,183],"First,":[78],"explore":[80],"hierarchical":[82],"property":[83],"semantics,":[87,157,194],"further":[89],"decompose":[90],"it":[91],"into":[92,140],"two":[93],"levels,":[94],"i.e.":[95],"discrete":[96,114,165,181],"semantics":[97],"holistic":[99,128,155,179],"Specifically,":[101],"visual":[103],"branch,":[104],"exploit":[106],"off-the-shelf":[108],"entity":[110,162],"predictor":[111],"generate":[113],"In":[117,148],"parallel,":[118],"trained":[120],"captioning":[122],"employed":[125],"output":[127],"As":[131],"textual":[134],"modality,":[135],"parse":[137],"text":[139],"three":[141,205],"parts":[142],"including":[143,208],"occurrence,":[144],"action":[145,160],"entity.":[147],"particular,":[149],"occurrence":[151],"corresponds":[152],"meanwhile":[158],"represent":[163],"ones.":[166],"Then,":[167],"different":[168],"graph":[169],"reasoning":[170],"techniques":[171],"are":[172],"utilized":[173],"promote":[175],"interaction":[177],"between":[178],"Extensive":[184],"experiments":[185],"demonstrate":[186],"that,":[187],"with":[188],"aid":[190],"our":[195],"method":[196],"achieves":[197],"superior":[199],"performance":[200],"over":[201],"state-of-the-art":[202],"on":[204],"benchmark":[206],"datasets,":[207],"MSR-VTT,":[209],"MSVD":[210],"DiDeMo.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}