{"id":"https://openalex.org/W4389539271","doi":"https://doi.org/10.1145/3610548.3618154","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","display_name":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","publication_year":2023,"publication_date":"2023-12-10","ids":{"openalex":"https://openalex.org/W4389539271","doi":"https://doi.org/10.1145/3610548.3618154"},"language":"en","primary_location":{"id":"doi:10.1145/3610548.3618154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610548.3618154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610548.3618154","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610548.3618154","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037338627","display_name":"Omri Avrahami","orcid":"https://orcid.org/0000-0002-7628-7525"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Omri Avrahami","raw_affiliation_strings":["The Hebrew University of Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022318529","display_name":"Kfir Aberman","orcid":"https://orcid.org/0000-0002-4958-601X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kfir Aberman","raw_affiliation_strings":["Google Research, United States of America"],"affiliations":[{"raw_affiliation_string":"Google Research, United States of America","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021513418","display_name":"Ohad Fried","orcid":"https://orcid.org/0000-0001-7109-4006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ohad Fried","raw_affiliation_strings":["Reichman University, Israel"],"affiliations":[{"raw_affiliation_string":"Reichman University, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Daniel Cohen-Or","raw_affiliation_strings":["Tel Aviv University, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091260693","display_name":"Dani Lischinski","orcid":"https://orcid.org/0000-0002-6191-0361"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dani Lischinski","raw_affiliation_strings":["The Hebrew University of Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037338627"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":13.5677,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.99304287,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.9861999750137329,"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":0.9794999957084656,"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":0.8632744550704956},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7088484764099121},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6598744988441467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5660368204116821},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5381712317466736},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4716740548610687},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4558784067630768},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.44869449734687805},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4482389986515045},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44177812337875366},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42641863226890564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392074406147003},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33829569816589355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33720269799232483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8632744550704956},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7088484764099121},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6598744988441467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5660368204116821},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5381712317466736},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4716740548610687},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4558784067630768},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.44869449734687805},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4482389986515045},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44177812337875366},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42641863226890564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392074406147003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33829569816589355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33720269799232483},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610548.3618154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610548.3618154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610548.3618154","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610548.3618154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610548.3618154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610548.3618154","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389539271.pdf","grobid_xml":"https://content.openalex.org/works/W4389539271.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W2961363059","https://openalex.org/W2962770929","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2985068832","https://openalex.org/W3035355202","https://openalex.org/W3035574324","https://openalex.org/W3102061158","https://openalex.org/W3122887115","https://openalex.org/W3155072588","https://openalex.org/W3168867926","https://openalex.org/W3173102319","https://openalex.org/W3178406257","https://openalex.org/W3216156094","https://openalex.org/W3216352822","https://openalex.org/W4225744354","https://openalex.org/W4281485151","https://openalex.org/W4285124635","https://openalex.org/W4286696412","https://openalex.org/W4287210973","https://openalex.org/W4298185919","https://openalex.org/W4310443798","https://openalex.org/W4312282373","https://openalex.org/W4312872987","https://openalex.org/W4312911498","https://openalex.org/W4319166718","https://openalex.org/W4321276804","https://openalex.org/W4385270985","https://openalex.org/W4385271055","https://openalex.org/W4385271281","https://openalex.org/W4385275531","https://openalex.org/W4385537219","https://openalex.org/W4386057725","https://openalex.org/W4386071604","https://openalex.org/W4386072096","https://openalex.org/W4386075631","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4386113271","https://openalex.org/W4390874575","https://openalex.org/W6611340967"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Text-to-image":[0],"model":[1,144],"personalization":[2],"aims":[3],"to":[4,9,44,73,164,167,180,191,207],"introduce":[5,52,185],"a":[6,28,45,60,64,75,119,126,133,147,160,174,187,221],"user-provided":[7],"concept":[8,30],"the":[10,24,53,86,95,102,113,143,153,193,218],"model,":[11],"allowing":[12],"its":[13],"synthesis":[14],"in":[15,36,199],"diverse":[16],"contexts.":[17],"However,":[18],"current":[19],"methods":[20],"primarily":[21],"focus":[22],"on":[23,177],"case":[25],"of":[26,55,63,104,135,195,229],"learning":[27],"single":[29,61],"from":[31],"multiple":[32,197],"images":[33],"with":[34,98],"variations":[35],"backgrounds":[37],"and":[38,40,155,215],"poses,":[39],"struggle":[41],"when":[42],"adapted":[43],"different":[46],"scenario.":[47],"In":[48],"this":[49,90],"work,":[50],"we":[51,71,92,225],"task":[54],"textual":[56,137],"scene":[57,65],"decomposition:":[58],"given":[59],"image":[62,97],"that":[66,100,131],"may":[67],"contain":[68],"several":[69,204,213,227],"concepts,":[70,171],"aim":[72],"extract":[74],"distinct":[76],"text":[77],"token":[78],"for":[79],"each":[80],"concept,":[81],"enabling":[82],"fine-grained":[83],"control":[84],"over":[85],"generated":[87,116,200],"scenes.":[88],"To":[89],"end,":[91],"propose":[93],"augmenting":[94],"input":[96],"masks":[99,108],"indicate":[101],"presence":[103],"target":[105],"concepts.":[106],"These":[107],"can":[109],"be":[110],"provided":[111],"by":[112,118,173],"user":[114,222],"or":[115],"automatically":[117],"pre-trained":[120],"segmentation":[121],"model.":[122],"We":[123,158,183,202],"then":[124],"present":[125],"novel":[127,175],"two-phase":[128],"customization":[129],"process":[130],"optimizes":[132],"set":[134],"dedicated":[136],"embeddings":[138],"(handles),":[139],"as":[140,142],"well":[141],"weights,":[145],"striking":[146],"delicate":[148],"balance":[149],"between":[150],"accurately":[151],"capturing":[152],"concepts":[154,198],"avoiding":[156],"overfitting.":[157],"employ":[159],"masked":[161],"diffusion":[162],"loss":[163,176],"enable":[165],"handles":[166],"generate":[168],"their":[169],"assigned":[170],"complemented":[172],"cross-attention":[178],"maps":[179],"prevent":[181],"entanglement.":[182],"also":[184],"union-sampling,":[186],"training":[188],"strategy":[189],"aimed":[190],"improve":[192],"ability":[194],"combining":[196],"images.":[201],"use":[203],"automatic":[205],"metrics":[206],"quantitatively":[208],"compare":[209],"our":[210,230],"method":[211],"against":[212],"baselines,":[214],"further":[216],"affirm":[217],"results":[219],"using":[220],"study.":[223],"Finally,":[224],"showcase":[226],"applications":[228],"method.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":57},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}