{"id":"https://openalex.org/W2808399042","doi":"https://doi.org/10.1145/3206025.3206064","title":"Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval","display_name":"Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2808399042","doi":"https://doi.org/10.1145/3206025.3206064","mag":"2808399042"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206064","doi":"https://doi.org/10.1145/3206025.3206064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3206064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3206064","source":{"id":"https://openalex.org/S4306419706","display_name":"International Conference on Multimedia Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3206064","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012973327","display_name":"Niluthpol Chowdhury Mithun","orcid":"https://orcid.org/0000-0003-3611-4141","observed_orcids":["https://orcid.org/0000-0003-3611-4141"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niluthpol Chowdhury Mithun","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754","observed_orcids":["https://orcid.org/0000-0001-7314-6754","https://orcid.org/0000-0003-2258-1291"]},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Carnegie Mellon University & Bosch Research and Technology Center, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University & Bosch Research and Technology Center, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210120115","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600","observed_orcids":["https://orcid.org/0000-0002-6663-8600"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004732580","display_name":"Amit K. Roy\u2013Chowdhury","orcid":"https://orcid.org/0000-0001-6690-9725","observed_orcids":["https://orcid.org/0000-0001-6690-9725"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit K. Roy-Chowdhury","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.764,"has_fulltext":true,"cited_by_count":256,"citation_normalized_percentile":{"value":0.97644446,"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":"19","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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":0.9951000213623047,"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":0.001500000013038516,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0013000000035390258,"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/joint-embedding","display_name":"joint embedding","score":0.7929999828338623},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.7680000066757202},{"id":"https://openalex.org/keywords/audio-visual-features","display_name":"audio-visual features","score":0.6309999823570251},{"id":"https://openalex.org/keywords/pairwise-ranking-loss","display_name":"pairwise ranking loss","score":0.9340000152587891},{"id":"https://openalex.org/keywords/multimodal-cues","display_name":"multimodal cues","score":0.6629999876022339},{"id":"https://openalex.org/keywords/text-video-retrieval","display_name":"video-text retrieval","score":0.43700000643730164},{"id":"https://openalex.org/keywords/msvd","display_name":"MSVD","score":0.7329999804496765},{"id":"https://openalex.org/keywords/msr-vtt","display_name":"MSR-VTT","score":0.9959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475214242935181},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.7717888951301575},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.718332052230835},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5819085240364075},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5624919533729553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381738543510437},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5353245139122009},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5195767879486084},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49027279019355774},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4864475429058075},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.43961039185523987},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43941280245780945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34814393520355225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3411104083061218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3292604684829712},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206025.3206064","doi":"https://doi.org/10.1145/3206025.3206064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3206064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3206064","source":{"id":"https://openalex.org/S4306419706","display_name":"International Conference on Multimedia Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3206025.3206064","doi":"https://doi.org/10.1145/3206025.3206064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3206064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3206064","source":{"id":"https://openalex.org/S4306419706","display_name":"International Conference on Multimedia Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1824974782","display_name":"CPS: Synergy: Collaborative Research: Extracting Time-Critical Situational Awareness from Resource Constrained Networks","funder_award_id":"1544969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3619066000","display_name":"EAGER: Joint Modeling and Querying of Social Media and Video Data","funder_award_id":"1746031","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808399042.pdf","grobid_xml":"https://content.openalex.org/works/W2808399042.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W877909479","https://openalex.org/W1527575280","https://openalex.org/W1573040851","https://openalex.org/W1614298861","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W1987063155","https://openalex.org/W2062955551","https://openalex.org/W2070753207","https://openalex.org/W2096479579","https://openalex.org/W2096733369","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2490414731","https://openalex.org/W2523993696","https://openalex.org/W2526286384","https://openalex.org/W2544224704","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2558358930","https://openalex.org/W2565656701","https://openalex.org/W2606473278","https://openalex.org/W2613031639","https://openalex.org/W2618264341","https://openalex.org/W2619082050","https://openalex.org/W2623327532","https://openalex.org/W2737030113","https://openalex.org/W2739181657","https://openalex.org/W2765977864","https://openalex.org/W2774267535","https://openalex.org/W2950726992","https://openalex.org/W2963350250","https://openalex.org/W2963389687","https://openalex.org/W2963899908","https://openalex.org/W2964121744","https://openalex.org/W6600020652"],"related_works":["https://openalex.org/W2910905530","https://openalex.org/W4281771666","https://openalex.org/W3196529233","https://openalex.org/W3174269019","https://openalex.org/W3190416739","https://openalex.org/W3157185431","https://openalex.org/W4392404186","https://openalex.org/W4320502794","https://openalex.org/W4412438752","https://openalex.org/W4392942165"],"abstract_inverted_index":{"Constructing":[0],"a":[1,22,76,92,110],"joint":[2,35],"representation":[3],"invariant":[4],"across":[5],"different":[6],"modalities":[7],"(e.g.,":[8],"video,":[9],"language)":[10],"is":[11],"of":[12,24],"significant":[13,129],"importance":[14],"in":[15,27,104],"many":[16],"multimedia":[17],"applications.":[18],"While":[19],"there":[20],"are":[21],"number":[23],"recent":[25],"successes":[26],"developing":[28],"effective":[29],"image-text":[30],"retrieval":[31,39,68],"methods":[32],"by":[33,91],"learning":[34],"representations,":[36],"the":[37,65,106,116,134],"video-text":[38,67],"task,":[40],"however,":[41],"has":[42],"not":[43],"been":[44],"explored":[45],"to":[46,56,133],"its":[47],"fullest":[48],"extent.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,74,99],"study":[54],"how":[55],"effectively":[57],"utilize":[58],"available":[59],"multimodal":[60],"cues":[61],"from":[62],"videos":[63],"for":[64,95,115],"cross-modal":[66],"task.":[69,117],"Based":[70],"on":[71,119],"our":[72,126],"analysis,":[73],"propose":[75,109],"novel":[77],"framework":[78],"that":[79,125],"simultaneously":[80],"utilizes":[81],"multi-modal":[82],"features":[83],"(different":[84],"visual":[85],"characteristics,":[86],"audio":[87],"inputs,":[88],"and":[89,108,121],"text)":[90],"fusion":[93],"strategy":[94],"efficient":[96],"retrieval.":[97],"Furthermore,":[98],"explore":[100],"several":[101],"loss":[102,114],"functions":[103],"training":[105],"embedding":[107],"modified":[111],"pairwise":[112],"ranking":[113],"Experiments":[118],"MSVD":[120],"MSR-VTT":[122],"datasets":[123],"demonstrate":[124],"method":[127],"achieves":[128],"performance":[130],"gain":[131],"compared":[132],"state-of-the-art":[135],"approaches.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":66},{"year":2021,"cited_by_count":58},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-21T00:00:00"}