{"id":"https://openalex.org/W2765262252","doi":"https://doi.org/10.1145/3126686.3126720","title":"Learning Social Image Embedding with Deep Multimodal Attention Networks","display_name":"Learning Social Image Embedding with Deep Multimodal Attention Networks","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2765262252","doi":"https://doi.org/10.1145/3126686.3126720","mag":"2765262252"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","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/1710.06582","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033233243","display_name":"Feiran Huang","orcid":"https://orcid.org/0000-0003-4294-0212"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462591","display_name":"Xiaoming Zhang","orcid":"https://orcid.org/0000-0002-6662-4102"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036786337","display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031511560","display_name":"Yueying He","orcid":"https://orcid.org/0000-0003-2082-3656"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueying He","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100722638","display_name":"Zhonghua Zhao","orcid":"https://orcid.org/0000-0001-9625-1119"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghua Zhao","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"460","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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":0.9983999729156494,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.783987820148468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7399811744689941},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.622413158416748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6185923218727112},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5203230381011963},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48494866490364075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4671829044818878},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4579841196537018},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43652352690696716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43132615089416504}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.783987820148468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399811744689941},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.622413158416748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6185923218727112},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5203230381011963},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48494866490364075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4671829044818878},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4579841196537018},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43652352690696716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43132615089416504},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3126686.3126720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.06582","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.06582","pdf_url":"https://arxiv.org/pdf/1710.06582","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:1710.06582","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.06582","pdf_url":"https://arxiv.org/pdf/1710.06582","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/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W219040644","https://openalex.org/W1514535095","https://openalex.org/W1523385540","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1888005072","https://openalex.org/W1905882502","https://openalex.org/W1909903157","https://openalex.org/W1931795219","https://openalex.org/W1949478088","https://openalex.org/W2007972815","https://openalex.org/W2023615142","https://openalex.org/W2031489346","https://openalex.org/W2062797058","https://openalex.org/W2070753207","https://openalex.org/W2090891622","https://openalex.org/W2100235303","https://openalex.org/W2108598243","https://openalex.org/W2123024445","https://openalex.org/W2125204570","https://openalex.org/W2154851992","https://openalex.org/W2155803963","https://openalex.org/W2393319904","https://openalex.org/W2397149706","https://openalex.org/W2510282234","https://openalex.org/W2527238922","https://openalex.org/W2592628593","https://openalex.org/W2598545596","https://openalex.org/W2909398847","https://openalex.org/W2949218037","https://openalex.org/W2950700180","https://openalex.org/W2963713828","https://openalex.org/W2963954913","https://openalex.org/W3103919331","https://openalex.org/W3104097132","https://openalex.org/W3105705953","https://openalex.org/W3177525997"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W3197494161","https://openalex.org/W4390452972","https://openalex.org/W3011727199"],"abstract_inverted_index":{"Learning":[0],"social":[1,31,61,71],"media":[2],"data":[3,56],"embedding":[4,50,73,126,148],"by":[5],"deep":[6,84,144],"models":[7],"has":[8],"attracted":[9],"extensive":[10],"research":[11],"interest":[12],"as":[13,15,22],"well":[14],"boomed":[16],"a":[17,69,83,105,128],"lot":[18],"of":[19,168,174,194],"applications,":[20],"such":[21],"link":[23,36,92],"prediction,":[24],"classification,":[25],"and":[26,38,44,91,117,155,177,197],"cross-modal":[27,178,198],"search.":[28,179,199],"However,":[29],"for":[30,125],"images":[32],"which":[33,81],"contain":[34],"both":[35,151],"information":[37],"multimodal":[39,89,101,106,153],"contents":[40,90,154],"(e.g.,":[41],"text":[42],"description,":[43],"visual":[45],"content),":[46],"simply":[47],"employing":[48],"the":[49,98,111,122,137,142,146,152,156,166,172,192],"learnt":[51,147],"from":[52],"network":[53,108,123,132,158],"structure":[54,124],"or":[55],"content":[57],"results":[58],"in":[59,171,191],"sub-optimal":[60],"image":[62,72,115,183],"representation.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,103],"propose":[68,104],"novel":[70,129],"approach":[74,170],"called":[75],"Deep":[76],"Multimodal":[77],"Attention":[78],"Networks":[79],"(DMAN),":[80],"employs":[82],"model":[85,136],"to":[86,95,109,135,164,181],"jointly":[87],"embed":[88],"information.":[93,159],"Specifically,":[94],"effectively":[96],"capture":[97,150],"correlations":[99],"between":[100,114],"contents,":[102],"attention":[107],"encode":[110],"fine-granularity":[112],"relation":[113],"regions":[116],"textual":[118],"words.":[119],"To":[120],"leverage":[121],"learning,":[127],"Siamese-Triplet":[130],"neural":[131],"is":[133],"proposed":[134,186],"links":[138],"among":[139],"images.":[140],"With":[141],"joint":[143],"model,":[145],"can":[149],"nonlinear":[157],"Extensive":[160],"experiments":[161],"are":[162],"conducted":[163],"investigate":[165],"effectiveness":[167],"our":[169,185],"applications":[173],"multi-label":[175,195],"classification":[176,196],"Compared":[180],"state-of-the-art":[182],"embeddings,":[184],"DMAN":[187],"achieves":[188],"significant":[189],"improvement":[190],"tasks":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}