{"id":"https://openalex.org/W4400822031","doi":"https://doi.org/10.1145/3658136","title":"Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model","display_name":"Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400822031","doi":"https://doi.org/10.1145/3658136"},"language":"en","primary_location":{"id":"doi:10.1145/3658136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658136","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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/A5101871022","display_name":"Zheng Gu","orcid":"https://orcid.org/0000-0001-9914-3922"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zheng Gu","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong","Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9914-3922","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007476607","display_name":"Shiyuan Yang","orcid":"https://orcid.org/0000-0001-8213-5803"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shiyuan Yang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong","Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-8213-5803","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013972536","display_name":"Jing Liao","orcid":"https://orcid.org/0000-0001-7014-5377"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Liao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7014-5377","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066091819","display_name":"Jing Huo","orcid":"https://orcid.org/0000-0002-8504-455X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huo","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8504-455X","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-1813","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9936,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74288843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"43","issue":"4","first_page":"1","last_page":"15"},"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":0.9991000294685364,"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":0.9991000294685364,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9969000220298767,"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":0.9962000250816345,"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":0.6373976469039917},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6171402335166931},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5175906419754028},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5039812922477722},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48774415254592896},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45530739426612854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45438987016677856},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08944198489189148},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06660234928131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373976469039917},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6171402335166931},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5175906419754028},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5039812922477722},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48774415254592896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45530739426612854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45438987016677856},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08944198489189148},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06660234928131104},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658136","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3054151883","display_name":null,"funder_award_id":"Grant 62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7016909273","display_name":null,"funder_award_id":"Grant 62276128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2156076339","https://openalex.org/W2292976057","https://openalex.org/W2470139095","https://openalex.org/W2594519801","https://openalex.org/W2611605760","https://openalex.org/W2956900569","https://openalex.org/W3036167779","https://openalex.org/W3048800544","https://openalex.org/W3169176371","https://openalex.org/W4214926101","https://openalex.org/W4221143046","https://openalex.org/W4292779060","https://openalex.org/W4294434188","https://openalex.org/W4312933868","https://openalex.org/W4367369792","https://openalex.org/W4384826610","https://openalex.org/W4385527149","https://openalex.org/W4386076112","https://openalex.org/W4386076215","https://openalex.org/W4389335076","https://openalex.org/W4390871920","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873795","https://openalex.org/W6600553734","https://openalex.org/W6601141708","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6788812206","https://openalex.org/W6843258702"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327","https://openalex.org/W2108687567","https://openalex.org/W2789220062"],"abstract_inverted_index":{"Visual":[0],"In-Context":[1],"Learning":[2],"(ICL)":[3],"has":[4,30],"emerged":[5],"as":[6],"a":[7,45,94,109,122,152,186],"promising":[8],"research":[9],"area":[10],"due":[11],"to":[12,15,35,37,68,84,127,145,157,192],"its":[13,33],"capability":[14,144],"accomplish":[16],"various":[17],"tasks":[18,39,191],"with":[19],"limited":[20],"example":[21],"pairs":[22],"through":[23],"analogical":[24],"reasoning.":[25],"However,":[26],"training-based":[27],"visual":[28,58,97,103,118,142,190],"ICL":[29,59,98],"limitations":[31],"in":[32,55,195],"ability":[34],"generalize":[36],"unseen":[38],"and":[40,76,104,150,172,183,212],"requires":[41],"the":[42,50,56,129,159,202],"collection":[43],"of":[44,161,189,204],"diverse":[46],"task":[47],"dataset.":[48],"On":[49],"other":[51],"hand,":[52],"existing":[53,208],"methods":[54],"inference-based":[57,96],"category":[60],"solely":[61],"rely":[62],"on":[63],"textual":[64,105,137],"prompts,":[65],"which":[66],"fail":[67],"capture":[69],"fine-grained":[70,130],"contextual":[71],"information":[72],"from":[73,82],"given":[74],"examples":[75],"can":[77],"be":[78,193],"time-consuming":[79],"when":[80],"converting":[81],"images":[83],"text":[85,148,166],"prompts.":[86,167],"To":[87],"address":[88],"these":[89],"challenges,":[90],"we":[91,120,139],"propose":[92,121],"Analogist,":[93],"novel":[95],"approach":[99],"that":[100],"exploits":[101],"both":[102,210],"prompting":[106],"techniques":[107],"using":[108],"text-to-image":[110],"diffusion":[111],"model":[112],"pretrained":[113],"for":[114],"image":[115,134],"inpainting.":[116],"For":[117,136],"prompting,":[119,138],"self-attention":[123],"cloning":[124],"(SAC)":[125],"method":[126,169,206],"guide":[128],"structural-level":[131],"analogy":[132,163],"between":[133],"examples.":[135],"leverage":[140],"GPT-4V's":[141],"reasoning":[143],"efficiently":[146],"generate":[147],"prompts":[149],"introduce":[151],"cross-attention":[153],"masking":[154],"(CAM)":[155],"operation":[156],"enhance":[158],"accuracy":[160],"semantic-level":[162],"guided":[164],"by":[165],"Our":[168,214],"is":[170,180,217],"out-of-the-box":[171],"does":[173],"not":[174],"require":[175],"fine-tuning":[176],"or":[177],"optimization.":[178],"It":[179],"also":[181],"generic":[182],"flexible,":[184],"enabling":[185],"wide":[187],"range":[188],"performed":[194],"an":[196],"in-context":[197],"manner.":[198],"Extensive":[199],"experiments":[200],"demonstrate":[201],"superiority":[203],"our":[205],"over":[207],"approaches,":[209],"qualitatively":[211],"quantitatively.":[213],"project":[215],"webpage":[216],"available":[218],"at":[219],"https://analogist2d.github.io.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}