{"id":"https://openalex.org/W3190981030","doi":"https://doi.org/10.24963/ijcai.2021/154","title":"Dig into Multi-modal Cues for Video Retrieval with Hierarchical Alignment","display_name":"Dig into Multi-modal Cues for Video Retrieval with Hierarchical Alignment","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3190981030","doi":"https://doi.org/10.24963/ijcai.2021/154","mag":"3190981030"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/154","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/154","pdf_url":"https://www.ijcai.org/proceedings/2021/0154.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0154.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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","Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","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/A5026072498","display_name":"Mengdan Zhang","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 Zhang","raw_affiliation_strings":["Youtu, Tencent","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu, Tencent","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/A5053752937","display_name":"Runnan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runnan Chen","raw_affiliation_strings":["The University of Hong Kong","The University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858601","display_name":"Guanyu Cai","orcid":"https://orcid.org/0000-0002-5210-7585"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Cai","raw_affiliation_strings":["Tongji University","Tongji University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017956591","display_name":"Penghao Zhou","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":"Penghao Zhou","raw_affiliation_strings":["Youtu, Tencent","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu, Tencent","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/A5103110081","display_name":"Pai Peng","orcid":"https://orcid.org/0000-0002-7129-6174"},"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 Peng","raw_affiliation_strings":["Youtu, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082173143","display_name":"Xiaowei Guo","orcid":"https://orcid.org/0000-0001-6526-2579"},"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":"Xiaowei Guo","raw_affiliation_strings":["Youtu, Tencent","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu, Tencent","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/A5071068569","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3230-6392"},"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"]},{"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":"Jian Wu","raw_affiliation_strings":["Zhejiang University","Zhejiang University, China","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004402130","display_name":"Xing Sun","orcid":"https://orcid.org/0000-0001-8132-9083"},"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 Sun","raw_affiliation_strings":["Youtu, Tencent","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu, Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1113","last_page":"1121"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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":0.996399998664856,"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":0.8567564487457275},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.634222149848938},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6153244376182556},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5718957185745239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5553250312805176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4510568380355835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4091223478317261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567564487457275},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.634222149848938},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6153244376182556},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5718957185745239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5553250312805176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4510568380355835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4091223478317261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/154","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/154","pdf_url":"https://www.ijcai.org/proceedings/2021/0154.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/154","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/154","pdf_url":"https://www.ijcai.org/proceedings/2021/0154.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3190981030.pdf","grobid_xml":"https://content.openalex.org/works/W3190981030.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1927052826","https://openalex.org/W2112912048","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2526050071","https://openalex.org/W2526286384","https://openalex.org/W2774267535","https://openalex.org/W2796207103","https://openalex.org/W2883429621","https://openalex.org/W2885775891","https://openalex.org/W2897439619","https://openalex.org/W2948859046","https://openalex.org/W2962964995","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2965458216","https://openalex.org/W2967344709","https://openalex.org/W2970597249","https://openalex.org/W2984008963","https://openalex.org/W3006320872","https://openalex.org/W3034875620","https://openalex.org/W3034882096","https://openalex.org/W3035012345","https://openalex.org/W3035043893","https://openalex.org/W3035265375","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035454331","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3043990051","https://openalex.org/W3081484346","https://openalex.org/W3122640483","https://openalex.org/W3197828817","https://openalex.org/W4287757777","https://openalex.org/W4288089799","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2847365777","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W3128025644","https://openalex.org/W2355048207"],"abstract_inverted_index":{"Multi-modal":[0],"cues":[1,25,58,86,123],"presented":[2],"in":[3,38,68,84],"videos":[4],"are":[5],"usually":[6],"beneficial":[7],"for":[8,33,87,109,124],"the":[9,48,73,80],"challenging":[10],"video-text":[11,75],"retrieval":[12,19,139],"task":[13],"on":[14,135],"internet-scale":[15],"datasets.":[16,140],"Recent":[17],"video":[18,138],"methods":[20,134],"take":[21],"advantage":[22],"of":[23,51],"multi-modal":[24,57,85,122],"by":[26],"aggregating":[27],"them":[28],"to":[29,44,77,98,120],"holistic":[30,116],"high-level":[31,101],"semantics":[32,53,92],"matching":[34],"with":[35,90],"text":[36],"representations":[37],"a":[39,100,115],"global":[40,46,125],"view.":[41],"In":[42],"contrast":[43],"this":[45,69],"alignment,":[47,129],"local":[49,91,112],"alignment":[50,76,89,113],"detailed":[52,81],"encoded":[54],"within":[55],"both":[56],"and":[59,114],"distinct":[60],"phrases":[61],"is":[62,107,118],"still":[63],"not":[64],"well":[65,96],"conducted.":[66],"Thus,":[67],"paper,":[70],"we":[71],"leverage":[72],"hierarchical":[74,128],"fully":[78],"explore":[79],"diverse":[82],"characteristics":[83],"fine-grained":[88],"from":[93],"phrases,":[94],"as":[95,97],"capture":[99],"semantic":[102],"correspondence.":[103],"Specifically,":[104],"multi-step":[105],"attention":[106],"learned":[108],"progressively":[110],"comprehensive":[111],"transformer":[117],"utilized":[119],"summarize":[121],"alignment.":[126],"With":[127],"our":[130],"model":[131],"outperforms":[132],"state-of-the-art":[133],"three":[136],"public":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}