{"id":"https://openalex.org/W3092767330","doi":"https://doi.org/10.1145/3394171.3413977","title":"Deep Multimodal Neural Architecture Search","display_name":"Deep Multimodal Neural Architecture Search","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092767330","doi":"https://doi.org/10.1145/3394171.3413977","mag":"3092767330"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026404286","display_name":"Yuhao Cui","orcid":"https://orcid.org/0009-0007-3644-7321"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Cui","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Cloud & AI, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud & AI, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6987,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.95870857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3743","last_page":"3752"},"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8481770157814026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6707382202148438},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6121065616607666},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5620077252388},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5170658230781555},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5165387988090515},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5056407451629639},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4805470108985901},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44270098209381104},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.42271849513053894},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41767412424087524},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4141325354576111},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.41261568665504456},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40925654768943787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481770157814026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6707382202148438},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6121065616607666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5620077252388},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5170658230781555},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5165387988090515},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5056407451629639},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4805470108985901},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44270098209381104},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.42271849513053894},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41767412424087524},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4141325354576111},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.41261568665504456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40925654768943787},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2121486117","https://openalex.org/W2151096985","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2546696630","https://openalex.org/W2552639984","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2747623286","https://openalex.org/W2804243936","https://openalex.org/W2962764817","https://openalex.org/W2962850006","https://openalex.org/W2962964995","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963176022","https://openalex.org/W2963717374","https://openalex.org/W2964067226","https://openalex.org/W2964080601","https://openalex.org/W2964081807","https://openalex.org/W2964120214","https://openalex.org/W2964185501","https://openalex.org/W2964345214","https://openalex.org/W2964345792","https://openalex.org/W2964444661","https://openalex.org/W2970231061","https://openalex.org/W2975501350","https://openalex.org/W3098232790","https://openalex.org/W3106250896"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W3093803775","https://openalex.org/W3197494161","https://openalex.org/W2563212008","https://openalex.org/W3013953798","https://openalex.org/W2477990774","https://openalex.org/W4390452972","https://openalex.org/W3011727199"],"abstract_inverted_index":{"Designing":[0],"effective":[1],"neural":[2,21,44],"networks":[3],"is":[4],"fundamentally":[5],"important":[6],"in":[7],"deep":[8,42,69],"multimodal":[9,43,51,55,103,142],"learning.":[10],"Most":[11],"existing":[12,137],"works":[13],"focus":[14],"on":[15],"a":[16,40,60,68,86,108],"single":[17],"task":[18],"and":[19,28,65,126,154],"design":[20],"architectures":[22,114],"manually,":[23],"which":[24],"are":[25,118],"highly":[26],"task-specific":[27,98],"hard":[29],"to":[30,32,81,100],"generalize":[31],"different":[33,102,116],"tasks.":[34,53,105],"In":[35],"this":[36],"paper,":[37],"we":[38,57,96],"devise":[39],"generalized":[41],"architecture":[45],"search":[46],"(MMnas)":[47],"framework":[48],"for":[49,115],"various":[50],"learning":[52,104,143],"Given":[54],"input,":[56],"first":[58],"define":[59],"set":[61],"of":[62,92],"primitive":[63],"operations,":[64],"then":[66],"construct":[67],"encoder-decoder":[70],"based":[71],"unified":[72,94],"backbone,":[73,95],"where":[74],"each":[75],"encoder":[76],"or":[77],"decoder":[78],"block":[79],"corresponds":[80],"an":[82],"operation":[83,88],"searched":[84],"from":[85],"predefined":[87],"pool.":[89],"On":[90],"top":[91],"the":[93,112,132],"attach":[97],"heads":[99],"tackle":[101],"By":[106],"using":[107],"gradient-based":[109],"NAS":[110],"algorithm,":[111],"optimal":[113],"tasks":[117,144],"learned":[119],"efficiently.":[120],"Extensive":[121],"ablation":[122],"studies,":[123],"comprehensive":[124],"analysis,":[125],"comparative":[127],"experimental":[128],"results":[129],"show":[130],"that":[131],"obtained":[133],"MMnasNet":[134],"significantly":[135],"outperforms":[136],"state-of-the-art":[138],"approaches":[139],"across":[140],"three":[141],"(over":[145],"five":[146],"datasets),":[147],"including":[148],"visual":[149,155],"question":[150],"answering,":[151],"image-text":[152],"matching,":[153],"grounding.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":15}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}