{"id":"https://openalex.org/W3174269019","doi":"https://doi.org/10.1109/icmew53276.2021.9455971","title":"Integrated Modalities And Multi-Level Granularity: Towards A Unified Video-Text Retrieval Framework","display_name":"Integrated Modalities And Multi-Level Granularity: Towards A Unified Video-Text Retrieval Framework","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3174269019","doi":"https://doi.org/10.1109/icmew53276.2021.9455971","mag":"3174269019"},"language":"en","primary_location":{"id":"doi:10.1109/icmew53276.2021.9455971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew53276.2021.9455971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia &amp; Expo Workshops (ICMEW)","raw_type":"proceedings-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/A5100324301","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-4218-8008"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000731827","display_name":"Wenzhe Wang","orcid":"https://orcid.org/0000-0001-7431-9039"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Wang","raw_affiliation_strings":["Zhejiang University,China","Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332500","display_name":"Zhijie Zhang","orcid":"https://orcid.org/0000-0003-1058-5930"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173363","display_name":"Mengdan Zhangz","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengdan Zhangz","raw_affiliation_strings":["Youtu Lab, Tencent,China","Youtu Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011849538","display_name":"Pai Pengz","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pai Pengz","raw_affiliation_strings":["Youtu Lab, Tencent,China","Youtu Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006428166","display_name":"Xing Sunz","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Sunz","raw_affiliation_strings":["Youtu Lab, Tencent,China","Youtu Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100324301"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37227124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.9965000152587891,"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":0.8330621719360352},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6625421047210693},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6076793074607849},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.586383581161499},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5530110001564026},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5262291431427002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5001988410949707},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4994363784790039},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42042088508605957},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41341888904571533},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41030949354171753},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.376156210899353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3573283553123474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3456040024757385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330621719360352},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6625421047210693},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6076793074607849},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.586383581161499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5530110001564026},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5262291431427002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001988410949707},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4994363784790039},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42042088508605957},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41341888904571533},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41030949354171753},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.376156210899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3573283553123474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3456040024757385},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew53276.2021.9455971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew53276.2021.9455971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia &amp; Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2078238240","https://openalex.org/W2425121537","https://openalex.org/W2883429621","https://openalex.org/W2963916161","https://openalex.org/W2972073579","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3043840704","https://openalex.org/W3043990051","https://openalex.org/W3081484346","https://openalex.org/W3094751268","https://openalex.org/W3122640483","https://openalex.org/W3197828817","https://openalex.org/W6779340355","https://openalex.org/W6781205876","https://openalex.org/W6782128855","https://openalex.org/W6784184991","https://openalex.org/W6784761581"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,64],"between":[2,100],"videos":[3,16],"and":[4,36,86,98,105,118,121,129],"texts":[5],"has":[6,67],"attracted":[7],"growing":[8],"attentions":[9],"due":[10],"to":[11],"the":[12,18,52,90,132],"rapid":[13],"emergence":[14],"of":[15,25,42,77,80,89,103],"on":[17],"web.":[19],"Recent":[20],"researches":[21],"handle":[22],"different":[23,78,101,106],"issues":[24],"this":[26,57],"task":[27],"such":[28],"as":[29],"exploiting":[30],"multi-modal":[31],"video":[32,107],"cues,":[33],"hierarchical":[34],"reasoning,":[35],"learning":[37,82],"pre-trained":[38],"models.":[39],"The":[40],"implementations":[41],"these":[43],"approaches":[44],"vary":[45],"a":[46,61,71],"lot,":[47],"which":[48],"brings":[49],"difficulty":[50],"for":[51,74,111,131],"further":[53,133],"research.":[54,134],"Therefore,":[55],"in":[56],"paper,":[58],"we":[59],"provide":[60],"unified":[62,126],"video-text":[63],"framework":[65,127],"that":[66,94],"following":[68],"features:":[69],"1)":[70],"modular":[72],"design":[73],"easy":[75],"modification":[76],"structures":[79],"deep":[81],"models;":[83],"2)":[84],"training":[85],"test":[87],"pipelines":[88],"state-of-the-art":[91],"(SOTA)":[92],"models":[93],"leverage":[95],"hierarchy":[96],"cues":[97],"interactions":[99],"levels":[102],"granularity":[104],"modalities;":[108],"3)":[109],"support":[110],"various":[112],"benchmark":[113],"datasets;":[114],"4)":[115],"demo":[116],"exhibitions":[117],"well":[119],"tested":[120],"documented.":[122],"We":[123],"hope":[124],"our":[125],"useful":[128],"efficient":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
