{"id":"https://openalex.org/W3206019042","doi":"https://doi.org/10.1145/3474085.3475241","title":"Fine-grained Cross-modal Alignment Network for Text-Video Retrieval","display_name":"Fine-grained Cross-modal Alignment Network for Text-Video Retrieval","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206019042","doi":"https://doi.org/10.1145/3474085.3475241","mag":"3206019042"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475241","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/A5057073729","display_name":"Ning Han","orcid":"https://orcid.org/0000-0002-0654-6026"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Han","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002820037","display_name":"Guangyi Xiao","orcid":"https://orcid.org/0000-0003-0625-0804"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyi Xiao","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396885","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2928-2692"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101296394","display_name":"Zeng YaWen","orcid":"https://orcid.org/0000-0003-1908-1157"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawen Zeng","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353471","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0001-5902-1824"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4373,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.94988821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3826","last_page":"3834"},"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":0.9983000159263611,"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":0.9959999918937683,"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":0.8389018177986145},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7274277806282043},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6436828374862671},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.590853214263916},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5902783274650574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5667134523391724},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5361226797103882},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4705814719200134},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4620686173439026},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4116743505001068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4015546441078186},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39164063334465027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34078916907310486},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3097328245639801},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21805667877197266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389018177986145},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7274277806282043},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6436828374862671},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.590853214263916},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5902783274650574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5667134523391724},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5361226797103882},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4705814719200134},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4620686173439026},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4116743505001068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4015546441078186},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39164063334465027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34078916907310486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3097328245639801},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21805667877197266},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475241","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":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1957706851","https://openalex.org/W2085487226","https://openalex.org/W2299467264","https://openalex.org/W2519887557","https://openalex.org/W2526198870","https://openalex.org/W2565656701","https://openalex.org/W2798354744","https://openalex.org/W2803088946","https://openalex.org/W2806331055","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2897152025","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963393391","https://openalex.org/W2963524571","https://openalex.org/W2972073579","https://openalex.org/W2975813532","https://openalex.org/W2979930345","https://openalex.org/W2982335217","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2991539277","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035635319","https://openalex.org/W3035733952","https://openalex.org/W3043840704","https://openalex.org/W3122640483","https://openalex.org/W3130796238","https://openalex.org/W3173415456"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Despite":[0],"the":[1,28,60,73,91,113,120,137,145],"recent":[2],"progress":[3],"of":[4,20,139],"cross-modal":[5,50,88,126],"text-to-video":[6],"retrieval":[7,56],"techniques,":[8],"their":[9],"performance":[10],"is":[11],"still":[12],"unsatisfactory.":[13],"Most":[14],"existing":[15],"works":[16],"follow":[17],"a":[18,22,64,102,108],"trend":[19],"learning":[21],"joint":[23],"embedding":[24],"space":[25],"to":[26,111,144],"measure":[27],"distance":[29],"between":[30,41,75,93,116],"global-level":[31],"or":[32],"local-level":[33],"textual":[34],"and":[35,44,83,97,118,133],"video":[36,42],"representation.":[37],"The":[38],"fine-grained":[39,125],"interactions":[40,74,92],"segments":[43],"phrases":[45,84,98],"are":[46,99],"usually":[47],"neglected":[48],"in":[49,54,81,85],"learning,":[51],"which":[52,71],"results":[53,129],"suboptimal":[55],"performances.":[57],"To":[58],"tackle":[59],"problem,":[61],"we":[62],"propose":[63],"novel":[65],"Fine-grained":[66],"Cross-modal":[67],"Alignment":[68],"Network":[69],"(FCA-Net),":[70],"considers":[72],"visual":[76,94],"semantic":[77,95],"units":[78,96],"(i.e.,":[79],"sub-actions/sub-events)":[80],"videos":[82],"sentences":[86],"for":[87,124],"alignment.":[89,127],"Specifically,":[90],"formulated":[100],"as":[101,142],"link":[103],"prediction":[104],"problem":[105],"optimized":[106],"by":[107],"graph":[109],"auto-encoder":[110],"obtain":[112],"explicit":[114],"relations":[115],"them":[117],"enhance":[119],"aligned":[121],"feature":[122],"representation":[123],"Experimental":[128],"on":[130],"MSR-VTT,":[131],"YouCook2,":[132],"VATEX":[134],"datasets":[135],"demonstrate":[136],"superiority":[138],"our":[140],"model":[141],"compared":[143],"state-of-the-art":[146],"method.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":16}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}