{"id":"https://openalex.org/W3007735756","doi":"https://doi.org/10.1145/3376067.3376090","title":"Improving Variational Auto-Encoder with Self-Attention and Mutual Information for Image Generation","display_name":"Improving Variational Auto-Encoder with Self-Attention and Mutual Information for Image Generation","publication_year":2019,"publication_date":"2019-12-20","ids":{"openalex":"https://openalex.org/W3007735756","doi":"https://doi.org/10.1145/3376067.3376090","mag":"3007735756"},"language":"en","primary_location":{"id":"doi:10.1145/3376067.3376090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3376067.3376090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Video and Image Processing","raw_type":"proceedings-article"},"type":"article","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/A5112906737","display_name":"Lizhi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lizhi Lin","raw_affiliation_strings":["School of Software of Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Software of Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114594132","display_name":"Xinyue Liu","orcid":"https://orcid.org/0000-0002-4063-5129"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Liu","raw_affiliation_strings":["School of Software of Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Software of Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000836998","display_name":"Wenxin Liang","orcid":"https://orcid.org/0000-0002-9166-3138"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Liang","raw_affiliation_strings":["School of Software of Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Software of Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112906737"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56767031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"167"},"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":0.9945999979972839,"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":0.9945999979972839,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9944999814033508,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/mutual-information","display_name":"Mutual information","score":0.6929411292076111},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6806269884109497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547020077705383},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5100005865097046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5081403255462646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47748443484306335},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.41795527935028076},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16514965891838074}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6929411292076111},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6806269884109497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547020077705383},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5100005865097046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5081403255462646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47748443484306335},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.41795527935028076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16514965891838074},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3376067.3376090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3376067.3376090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Video and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1959608418","https://openalex.org/W1981276685","https://openalex.org/W2099471712","https://openalex.org/W2100495367","https://openalex.org/W2133564696","https://openalex.org/W2166851633","https://openalex.org/W2173520492","https://openalex.org/W2577946330","https://openalex.org/W2581485081","https://openalex.org/W2887997457","https://openalex.org/W2949117887","https://openalex.org/W2951873722","https://openalex.org/W2951939904","https://openalex.org/W2952838738","https://openalex.org/W2962695743","https://openalex.org/W2962717182","https://openalex.org/W2962793481","https://openalex.org/W2963223306","https://openalex.org/W2963684088","https://openalex.org/W2963746531","https://openalex.org/W2963800509","https://openalex.org/W2963858765","https://openalex.org/W2964042872","https://openalex.org/W2964201867","https://openalex.org/W2964308564","https://openalex.org/W3038022805"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"When":[0],"Variational":[1],"Auto-Encoder":[2,76],"(VAE)":[3],"is":[4],"applied":[5],"to":[6,13,27,46,53],"the":[7,29,32,37,40,48,55,81],"image":[8],"generation":[9],"task,":[10],"it":[11],"tends":[12],"generate":[14,68],"images":[15],"with":[16],"blurred":[17],"borders.":[18],"To":[19],"solve":[20],"this":[21],"problem,":[22],"we":[23],"use":[24,44],"mutual":[25],"information":[26],"maximize":[28],"similarity":[30],"between":[31],"data":[33],"feature":[34],"generated":[35],"by":[36,80],"encoder":[38],"and":[39,43,74],"shallow":[41],"feature,":[42],"self-attention":[45],"weight":[47],"features":[49],"of":[50,57],"different":[51],"dimensions":[52],"increase":[54],"correlation":[56],"similar":[58],"features.":[59],"Our":[60],"experiments":[61],"show":[62],"that":[63],"our":[64],"Self-Attention":[65],"AE":[66],"can":[67],"higher":[69],"quality":[70],"samples":[71],"than":[72],"VAE":[73],"Wasserstein":[75],"(WAE),":[77],"as":[78],"measured":[79],"Freshet":[82],"Inception":[83],"Distance":[84],"(FID)":[85],"score.":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}