{"id":"https://openalex.org/W4417123813","doi":"https://doi.org/10.1109/wacv61042.2026.00091","title":"Beyond Realism: Learning the Art of Expressive Composition with StickerNet","display_name":"Beyond Realism: Learning the Art of Expressive Composition with StickerNet","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417123813","doi":"https://doi.org/10.1109/wacv61042.2026.00091"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.20957","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113855411","display_name":"Hongbo Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136330","display_name":"Personal Improvement Computer Systems","ror":"https://ror.org/02x3erj71","country_code":"US","type":"company","lineage":["https://openalex.org/I4210136330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Lu","raw_affiliation_strings":["Picsart AI Research Picsart Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Picsart AI Research Picsart Inc","institution_ids":["https://openalex.org/I4210136330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120723556","display_name":"David Kocharian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136330","display_name":"Personal Improvement Computer Systems","ror":"https://ror.org/02x3erj71","country_code":"US","type":"company","lineage":["https://openalex.org/I4210136330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kocharian","raw_affiliation_strings":["Picsart AI Research Picsart Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Picsart AI Research Picsart Inc","institution_ids":["https://openalex.org/I4210136330"]}]},{"author_position":"last","author":{"id":null,"display_name":"Humphrey Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["Georgia Institute of Technology,College of Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,College of Computing","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0292722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"869","last_page":"878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.1518000066280365,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.1518000066280365,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11559999734163284,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.09430000185966492,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.7498000264167786},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.644599974155426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6191999912261963},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.595300018787384},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5042999982833862},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.34310001134872437},{"id":"https://openalex.org/keywords/realism","display_name":"Realism","score":0.3328999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758899986743927},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.7498000264167786},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5418000221252441},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5042999982833862},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.20957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.20957","pdf_url":"https://arxiv.org/pdf/2511.20957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.20957","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.20957","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.20957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.20957","pdf_url":"https://arxiv.org/pdf/2511.20957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"a":[1,16,78,109,220],"widely":[2],"used":[3],"operation":[4],"in":[5,26,171,223],"image":[6,9,82],"editing":[7,28,151,161,173,208],"workflows,":[8],"composition":[10,76,83,116],"has":[11],"traditionally":[12],"been":[13],"studied":[14],"with":[15],"focus":[17],"on":[18,97,140,154],"achieving":[19],"visual":[20,158,224],"realism":[21],"and":[22,88,127,160,181,186,195,229],"semantic":[23],"plausibility.":[24],"However,":[25],"practical":[27],"scenarios":[29],"of":[30,46,81,204,214],"the":[31,74,115,202,211,215],"modern":[32],"content":[33,58],"creation":[34,159],"landscape,":[35],"many":[36],"compositions":[37],"are":[38],"not":[39],"intended":[40],"to":[41,56],"preserve":[42],"realism.":[43,233],"Instead,":[44],"users":[45,94],"online":[47,157],"platforms":[48],"motivated":[49],"by":[50,136],"gaining":[51],"community":[52],"recognition":[53],"often":[54],"aim":[55],"create":[57],"that":[59,84,112,133,190,226],"is":[60],"more":[61],"artistic,":[62],"playful,":[63],"or":[64],"socially":[65],"engaging.":[66],"Taking":[67],"inspiration":[68],"from":[69,148,206],"this":[70,103],"observation,":[71],"we":[72,106,143],"define":[73],"expressive":[75],"task,":[77],"new":[79,221],"formulation":[80],"embraces":[85],"stylistic":[86],"diversity":[87],"looser":[89],"placement":[90,120,167,199],"logic,":[91],"reflecting":[92,164],"how":[93],"edit":[95],"images":[96],"real-world":[98,207],"creative":[99],"platforms.":[100],"To":[101],"address":[102],"underexplored":[104],"problem,":[105],"present":[107],"StickerNet,":[108],"two-stage":[110],"framework":[111],"first":[113],"determines":[114],"type,":[117],"then":[118],"predicts":[119],"parameters":[121],"such":[122],"as":[123],"opacity,":[124],"mask,":[125],"location,":[126],"scale":[128],"accordingly.":[129],"Unlike":[130],"prior":[131],"work":[132,218],"constructs":[134],"datasets":[135],"simulating":[137],"object":[138],"placements":[139],"real":[141],"images,":[142],"directly":[144],"build":[145],"our":[146],"dataset":[147],"1.8":[149],"million":[150],"actions":[152],"collected":[153],"an":[155],"anonymous":[156],"platform,":[162],"each":[163],"user-community":[165],"validated":[166],"decisions.":[168],"This":[169,217],"grounding":[170],"authentic":[172],"behavior":[174],"ensures":[175],"strong":[176],"alignment":[177],"between":[178],"task":[179],"definition":[180],"training":[182],"supervision.":[183],"User":[184],"studies":[185],"quantitative":[187],"evaluations":[188],"show":[189],"StickerNet":[191],"outperforms":[192],"common":[193],"baselines":[194],"closely":[196],"matches":[197],"human":[198],"behavior,":[200],"demonstrating":[201],"effectiveness":[203],"learning":[205],"patterns":[209],"despite":[210],"inherent":[212],"ambiguity":[213],"task.":[216],"introduces":[219],"direction":[222],"understanding":[225],"emphasizes":[227],"expressiveness":[228],"user":[230],"intent":[231],"over":[232]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-28T00:00:00"}