{"id":"https://openalex.org/W4386942867","doi":"https://doi.org/10.1145/3581783.3612006","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","display_name":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4386942867","doi":"https://doi.org/10.1145/3581783.3612006"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.11082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100612957","display_name":"Chen Jiang","orcid":"https://orcid.org/0009-0003-7616-8926"},"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":"Chen Jiang","raw_affiliation_strings":["Artificial Intelligence Innovation and Incubation Institute, Fudan University & Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7616-8926","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Innovation and Incubation Institute, Fudan University & Ant Group, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423423","display_name":"Hong Liu","orcid":"https://orcid.org/0009-0002-2361-5721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2361-5721","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031500761","display_name":"Xuzheng Yu","orcid":"https://orcid.org/0009-0000-9752-799X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuzheng Yu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-9752-799X","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434918","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0004-1353-7541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-1353-7541","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101941144","display_name":"Yuan Cheng","orcid":"https://orcid.org/0000-0003-2502-9101"},"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":"Yuan Cheng","raw_affiliation_strings":["Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2502-9101","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101472360","display_name":"Jia Xu","orcid":"https://orcid.org/0009-0004-1163-513X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Xu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-1163-513X","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023862460","display_name":"Zhongyi Liu","orcid":"https://orcid.org/0000-0001-9478-8107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyi Liu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9478-8107","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086923590","display_name":"Qingpei Guo","orcid":"https://orcid.org/0009-0001-0521-9664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingpei Guo","raw_affiliation_strings":["Ant Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8638-6594","affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055732061","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-6401-6111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6401-6111","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019934281","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0003-1691-6817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1691-6817","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101723187","display_name":"Qi Yuan","orcid":"https://orcid.org/0009-0002-9377-5755"},"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":"Yuan Qi","raw_affiliation_strings":["Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-9377-5755","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4626","last_page":"4636"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9941999912261963,"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":0.8378223180770874},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5509426593780518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5325872898101807},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5055100917816162},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.45523881912231445},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4466651380062103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4439488351345062},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4179023802280426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41567879915237427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27434322237968445},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21991580724716187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378223180770874},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5509426593780518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5325872898101807},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5055100917816162},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45523881912231445},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4466651380062103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4439488351345062},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4179023802280426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41567879915237427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27434322237968445},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21991580724716187},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.11082","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11082","pdf_url":"https://arxiv.org/pdf/2309.11082","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.11082","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11082","pdf_url":"https://arxiv.org/pdf/2309.11082","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386942867.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1522301498","https://openalex.org/W1927052826","https://openalex.org/W2096733369","https://openalex.org/W2101746535","https://openalex.org/W2152790380","https://openalex.org/W2157133710","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2599674900","https://openalex.org/W2949461431","https://openalex.org/W2962784628","https://openalex.org/W2963017553","https://openalex.org/W2963263347","https://openalex.org/W2972073579","https://openalex.org/W2981851019","https://openalex.org/W3006320872","https://openalex.org/W3010805239","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3035724178","https://openalex.org/W3043840704","https://openalex.org/W3090114880","https://openalex.org/W3090556797","https://openalex.org/W3094502228","https://openalex.org/W3099206234","https://openalex.org/W3105232955","https://openalex.org/W3130796238","https://openalex.org/W3145807616","https://openalex.org/W3166396011","https://openalex.org/W3176799298","https://openalex.org/W3184203741","https://openalex.org/W3197804339","https://openalex.org/W3198377975","https://openalex.org/W3200114289","https://openalex.org/W3204588463","https://openalex.org/W3204670646","https://openalex.org/W3207042189","https://openalex.org/W3212304713","https://openalex.org/W4214689917","https://openalex.org/W4214926101","https://openalex.org/W4221146248","https://openalex.org/W4224035735","https://openalex.org/W4225106907","https://openalex.org/W4225384855","https://openalex.org/W4225414521","https://openalex.org/W4283385403","https://openalex.org/W4285296644","https://openalex.org/W4285606530","https://openalex.org/W4297166239","https://openalex.org/W4297808394","https://openalex.org/W4304014690","https://openalex.org/W4304080435","https://openalex.org/W4307106676","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312999114","https://openalex.org/W4313186260","https://openalex.org/W4322746912","https://openalex.org/W4386076424","https://openalex.org/W6600194071","https://openalex.org/W6790241037"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2032548952"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,41,64,90,164,233],"explosion":[4],"of":[5,34,60,66,96],"web":[6],"videos":[7],"makes":[8],"text-video":[9,57,210,242],"retrieval":[10,22,243],"increasingly":[11],"essential":[12],"and":[13,19,46,68,74,88,137,158,249],"popular":[14],"for":[15,56,118,208],"video":[16,75],"filtering,":[17],"recommendation,":[18],"search.":[20],"Text-video":[21],"aims":[23],"to":[24,38,71,84,92,114,130,151,181,196,224],"rank":[25],"relevant":[26],"text/video":[27],"higher":[28],"than":[29],"irrelevant":[30],"ones.":[31],"The":[32,212],"core":[33],"this":[35,104],"task":[36],"is":[37],"precisely":[39],"measure":[40],"cross-modal":[42,222],"similarity":[43,179],"between":[44],"texts":[45],"videos.":[47],"Recently,":[48],"contrastive":[49,107],"learning":[50,108],"methods":[51,238],"have":[52],"shown":[53],"promising":[54],"results":[55],"retrieval,":[58],"most":[59],"which":[61],"focus":[62],"on":[63,239],"construction":[65],"positive":[67],"negative":[69,86,133],"pairs":[70,87,134],"learn":[72],"text":[73],"representations.":[76],"Nevertheless,":[77],"they":[78],"do":[79],"not":[80],"pay":[81],"enough":[82],"attention":[83],"hard":[85,116,132,156,206],"lack":[89],"ability":[91],"model":[93,176,225],"different":[94],"levels":[95],"semantic":[97,178,227],"similarity.":[98],"To":[99],"address":[100],"these":[101,155],"two":[102,110],"issues,":[103],"paper":[105],"improves":[106],"using":[109],"novel":[111,125],"techniques.":[112],"First,":[113],"exploit":[115],"examples":[117],"robust":[119],"discriminative":[120],"power,":[121],"we":[122,148],"propose":[123],"a":[124,143,187],"Dual-Modal":[126],"Attention-Enhanced":[127],"Module":[128],"(DMAE)":[129],"mine":[131],"from":[135],"textual":[136],"visual":[138],"clues.":[139],"By":[140],"further":[141],"introducing":[142],"Negative-aware":[144],"InfoNCE":[145],"(NegNCE)":[146],"loss,":[147],"are":[149],"able":[150],"adaptively":[152],"identify":[153],"all":[154],"negatives":[157,207],"explicitly":[159],"highlight":[160],"their":[161],"impacts":[162],"in":[163],"training":[165],"loss.":[166],"Second,":[167],"our":[168],"work":[169],"argues":[170],"that":[171,232],"triplet":[172,200],"samples":[173,201],"can":[174],"better":[175],"fine-grained":[177,205],"compared":[180],"pairwise":[182],"samples.":[183],"We":[184],"thereby":[185],"present":[186],"new":[188],"Triplet":[189],"Partial":[190],"Margin":[191],"Contrastive":[192],"Learning":[193],"(TPM-CL)":[194],"module":[195],"construct":[197],"partial":[198],"order":[199],"by":[202],"automatically":[203],"generating":[204],"matched":[209],"pairs.":[211],"proposed":[213,234],"TPM-CL":[214],"designs":[215],"an":[216],"adaptive":[217],"token":[218],"masking":[219],"strategy":[220],"with":[221],"interaction":[223],"subtle":[226],"differences.":[228],"Extensive":[229],"experiments":[230],"demonstrate":[231],"approach":[235],"outperforms":[236],"existing":[237],"four":[240],"widely-used":[241],"datasets,":[244],"including":[245],"MSR-VTT,":[246],"MSVD,":[247],"DiDeMo":[248],"ActivityNet.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}