{"id":"https://openalex.org/W4408352536","doi":"https://doi.org/10.1109/icassp49660.2025.10890204","title":"Structural-Aware Disentangled Learning with CLIP for Hyperbolic Zero-Shot Sketch-Based Image Retrieval*","display_name":"Structural-Aware Disentangled Learning with CLIP for Hyperbolic Zero-Shot Sketch-Based Image Retrieval*","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352536","doi":"https://doi.org/10.1109/icassp49660.2025.10890204"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100700879","display_name":"Qing Zhang","orcid":"https://orcid.org/0000-0002-3489-1417"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Zhang","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010464164","display_name":"Xiangdong Su","orcid":"https://orcid.org/0000-0001-8061-1474"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"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":"5"},"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":0.9689000248908997,"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":0.9689000248908997,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9674000144004822,"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/T11448","display_name":"Face recognition and analysis","score":0.9595000147819519,"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/sketch","display_name":"Sketch","score":0.8515079617500305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418336868286133},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5956595540046692},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5405923128128052},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5119591951370239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.494672030210495},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.45790600776672363},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4572870135307312},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44597673416137695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16567692160606384},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05494379997253418}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8515079617500305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418336868286133},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5956595540046692},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5405923128128052},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5119591951370239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.494672030210495},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.45790600776672363},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4572870135307312},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44597673416137695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16567692160606384},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05494379997253418},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W2603445054","https://openalex.org/W2885402090","https://openalex.org/W2962747232","https://openalex.org/W2988772405","https://openalex.org/W2997645545","https://openalex.org/W3045735302","https://openalex.org/W3085694362","https://openalex.org/W3129072783","https://openalex.org/W3191326487","https://openalex.org/W3211258519","https://openalex.org/W4205175531","https://openalex.org/W4280652284","https://openalex.org/W4283815156","https://openalex.org/W4304091961","https://openalex.org/W4321770427","https://openalex.org/W4364302131","https://openalex.org/W4386065553","https://openalex.org/W4386075842","https://openalex.org/W4386076063","https://openalex.org/W4390871918","https://openalex.org/W4391795700","https://openalex.org/W4393180831","https://openalex.org/W4393182987","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2185495922"],"abstract_inverted_index":{"The":[0],"zero-shot":[1],"sketch-based":[2],"image":[3,107],"retrieval":[4,122,135],"task":[5],"faces":[6],"two":[7],"key":[8],"challenges:":[9],"domain":[10,89,93,116],"gap":[11],"and":[12,38,76,111],"knowledge":[13],"transfer.":[14],"Our":[15],"innovation":[16],"is":[17,43],"recognizing":[18],"that":[19,73,140],"directly":[20],"aligning":[21],"cross-domain":[22],"features":[23,86,123],"weakens":[24],"the":[25,29,34,47,52,55,92,96,115,121],"discriminative":[26],"ability":[27],"of":[28,54,95],"model,":[30],"as":[31],"it":[32],"overlooks":[33],"asymmetry":[35],"between":[36],"sketches":[37],"images.":[39],"Additionally,":[40],"Euclidean":[41],"space":[42,126],"inadequate":[44],"for":[45],"capturing":[46],"hierarchical":[48,129],"structure,":[49],"which":[50],"limits":[51],"performance":[53,145],"model":[56],"on":[57,146],"complex":[58],"data.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"we":[64,80,99,119],"propose":[65],"a":[66,101],"Structural-Aware":[67],"Disentangled":[68],"Learning":[69],"network":[70],"(termed":[71],"SADLnet)":[72],"incorporates":[74],"CLIP":[75,82],"hyperbolic":[77,125],"geometry.":[78],"Specifically,":[79],"use":[81],"to":[83,90,105,127],"extract":[84],"visual":[85],"from":[87],"each":[88],"enhance":[91],"generalization":[94],"model.":[97],"Furthermore,":[98],"design":[100],"structure-guided":[102],"disentanglement":[103],"strategy":[104],"decompose":[106],"representations":[108],"into":[109,124],"sketch-related":[110],"sketch-unrelated":[112],"features,":[113],"addressing":[114],"gap.":[117],"Moreover,":[118],"project":[120],"capture":[128],"information,":[130],"improving":[131],"feature":[132],"discrimination":[133],"in":[134],"tasks.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"SADLnet":[141],"establishes":[142],"new":[143],"state-of-the-art":[144],"three":[147],"datasets.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}