{"id":"https://openalex.org/W2767169246","doi":"https://doi.org/10.1145/3123266.3123332","title":"Improved Multimodal Representation Learning with Skip Connections","display_name":"Improved Multimodal Representation Learning with Skip Connections","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2767169246","doi":"https://doi.org/10.1145/3123266.3123332","mag":"2767169246"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123332","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th 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/A5100729421","display_name":"Ning Zhang","orcid":"https://orcid.org/0000-0001-8128-7573"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Zhang","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780032","display_name":"Yu Cao","orcid":"https://orcid.org/0000-0001-8624-1099"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077348938","display_name":"Benyuan Liu","orcid":"https://orcid.org/0000-0002-7543-1054"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benyuan Liu","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003621523","display_name":"Yan Luo","orcid":"https://orcid.org/0000-0002-5301-5092"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Luo","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"654","last_page":"662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324418663978577},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7885985970497131},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6739425659179688},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6361924409866333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5979401469230652},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5611922740936279},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.49741461873054504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4871616065502167},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43073582649230957},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3724590539932251},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3336823582649231},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1053379476070404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324418663978577},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7885985970497131},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6739425659179688},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6361924409866333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979401469230652},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5611922740936279},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.49741461873054504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4871616065502167},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43073582649230957},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3724590539932251},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3336823582649231},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1053379476070404},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123332","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7034387563","display_name":null,"funder_award_id":"1738965, 1547428, 1541434, 1440737, 1229213, 1156639","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"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W189596042","https://openalex.org/W1026270304","https://openalex.org/W1497960466","https://openalex.org/W1505878979","https://openalex.org/W1523385540","https://openalex.org/W1536675765","https://openalex.org/W1606458877","https://openalex.org/W1665214252","https://openalex.org/W1855112655","https://openalex.org/W1883346539","https://openalex.org/W1950831375","https://openalex.org/W1999726054","https://openalex.org/W2006031689","https://openalex.org/W2025341678","https://openalex.org/W2063036810","https://openalex.org/W2064675550","https://openalex.org/W2098617596","https://openalex.org/W2099471712","https://openalex.org/W2100002341","https://openalex.org/W2105582566","https://openalex.org/W2107215754","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2119717200","https://openalex.org/W2124101779","https://openalex.org/W2125972593","https://openalex.org/W2127107099","https://openalex.org/W2129625650","https://openalex.org/W2130055251","https://openalex.org/W2136922672","https://openalex.org/W2148463593","https://openalex.org/W2148862211","https://openalex.org/W2151691375","https://openalex.org/W2152790380","https://openalex.org/W2155803963","https://openalex.org/W2164587673","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2259167532","https://openalex.org/W2408074187","https://openalex.org/W2473934411","https://openalex.org/W2504108613","https://openalex.org/W2618530766","https://openalex.org/W2949117887","https://openalex.org/W2951493172","https://openalex.org/W3004970274","https://openalex.org/W3004985245","https://openalex.org/W4285719527","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2916681395","https://openalex.org/W2529583158","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3008584592","https://openalex.org/W2810292802","https://openalex.org/W2775568836"],"abstract_inverted_index":{"Multimodal":[0],"Deep":[1],"Boltzmann":[2],"Machines":[3],"(DBMs)":[4],"have":[5],"demonstrated":[6],"huge":[7],"successes":[8],"in":[9],"multimodal":[10],"representation":[11],"learning":[12],"tasks.":[13],"During":[14],"inference,":[15],"DBMs":[16],"function":[17],"as":[18],"Recurrent":[19],"Neural":[20],"Nets":[21],"(RNNs)":[22],"because":[23],"of":[24,98,130],"the":[25,30,48,64,82,96,115,144],"intractable":[26],"distributions.":[27],"To":[28],"learn":[29],"parameters,":[31],"optimizations":[32],"can":[33,61,118,139],"alternatively":[34],"be":[35],"operated":[36],"on":[37,109,143],"these":[38],"surrogate":[39],"RNNs":[40],"with":[41],"\"truncated":[42],"message":[43],"passing\".":[44],"As":[45],"a":[46,53,127],"consequence,":[47],"gradient":[49],"will":[50],"propagate":[51],"through":[52],"long":[54],"chain":[55],"without":[56],"any":[57],"local":[58,93],"guidance":[59],"which":[60],"potentially":[62],"affects":[63],"optimization":[65],"procedure.":[66],"In":[67],"this":[68,72],"paper,":[69],"we":[70,90,113],"address":[71],"problem":[73],"by":[74],"adding":[75],"skip":[76,88],"connections":[77],"during":[78],"back-propagation":[79],"while":[80,125],"keeping":[81],"forward":[83],"propagation":[84],"(inference)":[85],"untouched.":[86],"With":[87],"connections,":[89],"implicitly":[91],"assign":[92],"\"targets\"":[94],"for":[95],"states":[97],"intermediate":[99],"inference":[100],"loops":[101],"to":[102,105,121],"approach.":[103],"Applied":[104],"different":[106,110],"training":[107,131],"criteria":[108],"data":[111,150],"sets,":[112],"demonstrate":[114],"proposed":[116],"algorithms":[117,138],"consistently":[119],"help":[120],"train":[122],"better":[123],"models":[124],"at":[126],"lower":[128],"cost":[129],"time.":[132],"Experimental":[133],"results":[134],"show":[135],"that":[136],"our":[137],"achieve":[140],"state-of-the-art":[141],"performance":[142],"Multimedia":[145],"Information":[146],"Retrieval":[147],"(MIR)":[148],"Flickr":[149],"set.":[151]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}