{"id":"https://openalex.org/W3207042189","doi":"https://doi.org/10.1145/3474085.3475515","title":"HANet","display_name":"HANet","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207042189","doi":"https://doi.org/10.1145/3474085.3475515","mag":"3207042189"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5032693575","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0003-2938-6798"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["Xidian University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University, Guangzhou, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017511861","display_name":"Xiangteng He","orcid":"https://orcid.org/0000-0001-8502-5685"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangteng He","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034814310","display_name":"Mingqian Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqian Tang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016207654","display_name":"Yiliang Lv","orcid":"https://orcid.org/0000-0002-3101-5569"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiliang Lv","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Xidian University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University, Guangzhou, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.105,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.95742982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3518","last_page":"3527"},"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":0.9986000061035156,"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":0.9962000250816345,"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":0.8215727806091309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5534586310386658},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5410728454589844},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5052219033241272},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48038822412490845},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4673866033554077},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45530998706817627},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44438275694847107},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41623690724372864},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3707456588745117},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14673811197280884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215727806091309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5534586310386658},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5410728454589844},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5052219033241272},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48038822412490845},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4673866033554077},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45530998706817627},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44438275694847107},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41623690724372864},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3707456588745117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14673811197280884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2565656701","https://openalex.org/W2616994964","https://openalex.org/W2752782242","https://openalex.org/W2753311918","https://openalex.org/W2808399042","https://openalex.org/W2884293275","https://openalex.org/W2897439619","https://openalex.org/W2950082793","https://openalex.org/W2950512756","https://openalex.org/W2956018683","https://openalex.org/W2956335072","https://openalex.org/W2962964995","https://openalex.org/W2963420686","https://openalex.org/W2963524571","https://openalex.org/W2972073579","https://openalex.org/W2975813532","https://openalex.org/W2981716253","https://openalex.org/W2981951787","https://openalex.org/W2989322838","https://openalex.org/W2997297138","https://openalex.org/W3007938835","https://openalex.org/W3013498424","https://openalex.org/W3015643935","https://openalex.org/W3035212740","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035635319","https://openalex.org/W3040166514","https://openalex.org/W3040892440","https://openalex.org/W3043840704","https://openalex.org/W3047397378","https://openalex.org/W3081484346","https://openalex.org/W3089682612","https://openalex.org/W3091880970","https://openalex.org/W3093002089","https://openalex.org/W3102887392","https://openalex.org/W3103717910","https://openalex.org/W3107973541","https://openalex.org/W3118694826","https://openalex.org/W3130796238","https://openalex.org/W3134566480","https://openalex.org/W3137521176","https://openalex.org/W3172655693"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W4312490297","https://openalex.org/W2032548952"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1],"is":[2,200,239],"an":[3],"important":[4],"yet":[5],"challenging":[6],"task":[7],"in":[8,132],"vision-language":[9],"understanding,":[10],"which":[11,228],"aims":[12],"to":[13,27,91],"learn":[14],"a":[15,86],"joint":[16],"embedding":[17],"space":[18],"where":[19,136],"related":[20],"video":[21,103,155,170,180],"and":[22,41,104,113,117,119,122,146,157,160,171,181,218,235],"text":[23,105],"instances":[24],"are":[25],"close":[26],"each":[28],"other.":[29],"Most":[30],"current":[31],"works":[32,60],"simply":[33],"measure":[34],"the":[35,45,54,62,70,74,81,133,137,142,152,165,168,187,190,221,230],"video-text":[36,77,97],"similarity":[37],"based":[38],"on":[39,125,141,151,164,212],"video-level":[40],"text-level":[42],"embeddings.":[43],"However,":[44],"neglect":[46],"of":[47,56,76,189,232],"more":[48],"fine-grained":[49],"or":[50],"local":[51,63,148],"information":[52,192],"causes":[53],"problem":[55],"insufficient":[57],"representation.":[58,78],"Some":[59],"exploit":[61],"details":[64],"by":[65,204],"disentangling":[66],"sentences,":[67],"but":[68],"overlook":[69],"corresponding":[71],"videos,":[72],"causing":[73],"asymmetry":[75],"To":[79],"address":[80],"above":[82],"limitations,":[83],"we":[84,100,127],"propose":[85],"Hierarchical":[87],"Alignment":[88],"Network":[89],"(HANet)":[90],"align":[92],"different":[93],"level":[94,139,149,162,174],"representations":[95,131],"for":[96],"matching.":[98],"Specifically,":[99],"first":[101],"decompose":[102],"into":[106],"three":[107,194],"semantic":[108,195,208],"levels,":[109],"namely":[110,216],"event":[111],"(video":[112],"text),":[114],"action":[115],"(motion":[116],"verb),":[118],"entity":[120],"(appearance":[121],"noun).":[123],"Based":[124],"these,":[126],"naturally":[128],"construct":[129],"hierarchical":[130,233],"individual-local-global":[134],"manner,":[135],"individual":[138],"focuses":[140,150,163],"alignment":[143,153,166],"between":[144,154,167,179],"frame":[145],"word,":[147],"clip":[156],"textual":[158],"context,":[159],"global":[161],"whole":[169],"text.":[172],"Different":[173],"alignments":[175],"capture":[176],"fine-to-coarse":[177],"correlations":[178],"text,":[182],"as":[183,185],"well":[184],"take":[186],"advantage":[188],"complementary":[191],"among":[193],"levels.":[196],"Besides,":[197],"our":[198],"HANet":[199,223],"also":[201],"richly":[202],"interpretable":[203],"explicitly":[205],"learning":[206],"key":[207],"concepts.":[209],"Extensive":[210],"experiments":[211],"two":[213],"public":[214],"datasets,":[215],"MSR-VTT":[217],"VATEX,":[219],"show":[220],"proposed":[222],"outperforms":[224],"other":[225],"state-of-the-art":[226],"methods,":[227],"demonstrates":[229],"effectiveness":[231],"representation":[234],"alignment.":[236],"Our":[237],"code":[238],"publicly":[240],"available":[241],"at":[242],"https://github.com/Roc-Ng/HANet.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2021-10-25T00:00:00"}