{"id":"https://openalex.org/W7147741389","doi":"https://doi.org/10.1109/cnml68938.2026.11452506","title":"SpatialDisen: Spatially Consistent Attention Regularization with Semantic Anchor Guidance for Multi-Concept Disentanglement","display_name":"SpatialDisen: Spatially Consistent Attention Regularization with Semantic Anchor Guidance for Multi-Concept Disentanglement","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147741389","doi":"https://doi.org/10.1109/cnml68938.2026.11452506"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5026782331","display_name":"Chaoying Liu","orcid":"https://orcid.org/0000-0003-0484-9522"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chun Liu","raw_affiliation_strings":["Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132644694","display_name":"Li Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhou","raw_affiliation_strings":["Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132575401","display_name":"Yuqiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiang Li","raw_affiliation_strings":["Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer and Artificial Intelligence,Wuhan,China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026782331"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92929171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"516"},"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":0.32260000705718994,"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":0.32260000705718994,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.19099999964237213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.1873999983072281,"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/embedding","display_name":"Embedding","score":0.5609999895095825},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.510699987411499},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4702000021934509},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4523000121116638},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.38749998807907104},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5935999751091003},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44519999623298645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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":11,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4389539271","https://openalex.org/W4390874393","https://openalex.org/W4390874575","https://openalex.org/W4402754193","https://openalex.org/W4409262065","https://openalex.org/W4410907380","https://openalex.org/W4413145060","https://openalex.org/W7131892374"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,72,119],"text-to-image":[3],"diffusion":[4],"models":[5],"have":[6],"revolutionized":[7],"customized":[8,121],"image":[9,20,122],"generation.":[10],"However,":[11],"disentangling":[12],"multiple":[13],"target":[14,70],"concepts":[15],"from":[16,27],"a":[17,22,41,48,63,79,126],"single":[18,127],"reference":[19,128],"remains":[21],"significant":[23],"challenge,":[24],"often":[25],"suffering":[26],"concept":[28,109],"entanglement":[29],"(visual":[30],"fusion)":[31],"and":[32,62,93,104,139],"representation":[33],"distortion.":[34],"To":[35],"address":[36],"this,":[37],"we":[38,46,77],"propose":[39,78],"SpatialDisen,":[40],"novel":[42],"two-stage":[43],"framework.":[44],"First,":[45],"introduce":[47],"text":[49,132],"embedding":[50],"learning":[51],"stage":[52,83],"with":[53],"Semantic":[54],"Anchor":[55],"Guidance":[56],"(SAG),":[57],"which":[58],"leverages":[59],"super-category":[60],"anchors":[61],"dynamic":[64],"template":[65],"sampling":[66],"strategy":[67],"to":[68],"align":[69],"embeddings":[71],"the":[73],"semantic":[74],"space.":[75],"Second,":[76],"cross-attention":[80],"map":[81],"optimization":[82],"utilizing":[84],"spatially":[85],"consistent":[86],"regularization,":[87],"combining":[88],"edge-sensitive":[89],"Jensen-Shannon":[90],"(JS)":[91],"divergence":[92],"Earth":[94],"Mover\u2019s":[95],"Distance":[96],"(EMD).":[97],"This":[98],"dual-metric":[99],"approach":[100],"calibrates":[101],"pixel-level":[102],"precision":[103],"global":[105],"layout,":[106],"ensuring":[107],"distinct":[108],"separation.":[110],"Comprehensive":[111],"experiments":[112],"demonstrate":[113],"that":[114],"SpatialDisen":[115],"outperforms":[116],"existing":[117],"methods":[118],"multi-concept":[120],"generation":[123],"based":[124],"on":[125],"image,":[129],"maintaining":[130],"competitive":[131],"alignment":[133],"while":[134],"achieving":[135],"optimal":[136],"visual":[137],"fidelity":[138],"balanced":[140],"expression":[141],"capability":[142],"across":[143],"different":[144],"concepts.":[145]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}