{"id":"https://openalex.org/W7163695008","doi":"https://doi.org/10.1145/3799902.3811186","title":"MAOAM: Unified Object and Material Selection with Vision-Language Models","display_name":"MAOAM: Unified Object and Material Selection with Vision-Language Models","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7163695008","doi":"https://doi.org/10.1145/3799902.3811186"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811186","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137954651","display_name":"Jaden Park","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaden Park","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, Wisconsin, USA"],"raw_orcid":"https://orcid.org/0000-0003-1901-4157","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015425468","display_name":"Valentin Deschaintre","orcid":"https://orcid.org/0000-0002-6219-3747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valentin Deschaintre","raw_affiliation_strings":["Adobe Research, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6219-3747","affiliations":[{"raw_affiliation_string":"Adobe Research, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138010552","display_name":"Jason Kuen","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Kuen","raw_affiliation_strings":["Adobe Research, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0001-5099-8145","affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137924248","display_name":"Kangning Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangning Liu","raw_affiliation_strings":["Adobe, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-0187-4602","affiliations":[{"raw_affiliation_string":"Adobe, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013165810","display_name":"Iliyan Georgiev","orcid":"https://orcid.org/0000-0002-9655-2138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iliyan Georgiev","raw_affiliation_strings":["Adobe Research, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-9655-2138","affiliations":[{"raw_affiliation_string":"Adobe Research, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137931804","display_name":"Krishna Kumar Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Kumar Singh","raw_affiliation_strings":["Adobe Research, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-8066-6835","affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137993455","display_name":"Yong Jae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Jae Lee","raw_affiliation_strings":["Adobe Research, San Jose, USA and University of Wisconsin-Madison, Madison, Wisconsin, USA"],"raw_orcid":"https://orcid.org/0000-0001-9863-1270","affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, USA and University of Wisconsin-Madison, Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081610985","display_name":"Michael Fischer","orcid":"https://orcid.org/0000-0002-2610-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Fischer","raw_affiliation_strings":["Adobe Research, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2610-4831","affiliations":[{"raw_affiliation_string":"Adobe Research, London, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.5558000206947327,"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":0.5558000206947327,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3375999927520752,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.010400000028312206,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7465999722480774},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6330000162124634},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.5947999954223633},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5551999807357788},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.54339998960495},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5277000069618225},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4620000123977661},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46140000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937999963760376},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7465999722480774},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6019999980926514},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.5947999954223633},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4620000123977661},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3799902.3811186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811186","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.04880","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.04880","pdf_url":"https://arxiv.org/pdf/2606.04880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811186","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Selection":[0],"is":[1],"a":[2,20,72,76,92],"core":[3],"operation":[4],"in":[5,75,99],"interactive":[6],"image":[7],"editing,":[8],"enabling":[9],"tasks":[10,62],"such":[11,52],"as":[12,53],"composition":[13],"or":[14,36,66],"manipulation.":[15],"To":[16],"be":[17,23,58],"practically":[18],"useful,":[19],"user":[21],"should":[22,42],"able":[24],"to":[25],"specify":[26],"and":[27,39,88],"disambiguate":[28],"the":[29,40],"desired":[30],"selection":[31,56,83],"region":[32],"through":[33],"either":[34],"text-":[35],"click-based":[37],"interactions,":[38],"system":[41],"support":[43,90],"selecting":[44],"not":[45],"only":[46,91],"objects":[47],"but":[48],"also":[49],"other":[50],"criteria,":[51],"materials.":[54],"Material-based":[55],"can":[57],"particularly":[59],"valuable":[60],"for":[61],"like":[63],"re-texturing":[64],"surfaces":[65],"consistently":[67],"editing":[68,101],"all":[69],"instances":[70],"of":[71],"specific":[73],"material":[74],"scene.":[77],"However,":[78],"existing":[79],"vision\u2013language-model":[80],"(VLM)":[81],"based":[82],"methods":[84],"are":[85],"largely":[86],"object-centric":[87],"typically":[89],"single":[93],"interaction":[94],"modality,":[95],"limiting":[96],"their":[97],"applicability":[98],"real":[100],"workflows.":[102]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-06-06T00:00:00"}