{"id":"https://openalex.org/W4417073183","doi":"https://doi.org/10.1145/3743093.3770959","title":"Learn Concepts from Multi-Scale Visual Information for Compositional Zero-Shot Learning","display_name":"Learn Concepts from Multi-Scale Visual Information for Compositional Zero-Shot Learning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073183","doi":"https://doi.org/10.1145/3743093.3770959"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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/10.1145/3743093.3770959","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064274008","display_name":"Gengchen Wang","orcid":"https://orcid.org/0009-0005-3612-9767"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Wang","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3612-9767","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042812101","display_name":"Zhijie Tan","orcid":"https://orcid.org/0000-0003-4934-1001"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Tan","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4934-1001","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Chu","orcid":"https://orcid.org/0009-0002-3330-0037"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chu","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3330-0037","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049684801","display_name":"Xinrong Chen","orcid":"https://orcid.org/0009-0009-0343-5265"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrong Chen","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0343-5265","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059356240","display_name":"Tong Mo","orcid":"https://orcid.org/0000-0002-3564-4610"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Mo","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3564-4610","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085128839","display_name":"Weiping Li","orcid":"https://orcid.org/0000-0003-2958-3097"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Li","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2958-3097","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18093793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9815000295639038,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9815000295639038,"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":0.005100000184029341,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4812000095844269},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3763999938964844},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3650999963283539},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35670000314712524},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.34689998626708984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6549000144004822},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073183.pdf","grobid_xml":"https://content.openalex.org/works/W4417073183.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2093848332","https://openalex.org/W2150884987","https://openalex.org/W2194775991","https://openalex.org/W2596142952","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2963960318","https://openalex.org/W2986385672","https://openalex.org/W3035084814","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3174350209","https://openalex.org/W4246233237","https://openalex.org/W4281722009","https://openalex.org/W4312539810","https://openalex.org/W4312578829","https://openalex.org/W4386065859","https://openalex.org/W4386171637","https://openalex.org/W4393154717","https://openalex.org/W4393154971","https://openalex.org/W4394597571","https://openalex.org/W4402772357","https://openalex.org/W4403468740","https://openalex.org/W4403827186"],"related_works":[],"abstract_inverted_index":{"Compositional":[0],"Zero-Shot":[1],"Learning":[2],"(CZSL)":[3],"aims":[4],"at":[5],"recognizing":[6],"novel":[7],"compositions":[8,26],"by":[9,44,54,94],"combining":[10],"concepts":[11,39,120],"learned":[12],"from":[13,40,121],"seen":[14],"compositions.":[15],"The":[16],"key":[17],"to":[18,36,82,111,115],"tackle":[19],"CZSL":[20,129],"is":[21],"disentangling":[22],"highly":[23],"coupled":[24],"attribute-object":[25],"and":[27,67,72,87,105,118,144],"learning":[28,63],"exclusive":[29],"concepts.":[30],"Previous":[31],"works":[32],"mainly":[33],"design":[34],"networks":[35],"learn":[37,119],"visual":[38,45,48,85,123],"top-layer":[41],"representations":[42],"provided":[43],"backbones.":[46],"As":[47],"backbones":[49],"progressively":[50],"integrate":[51],"information":[52,60],"layer":[53],"layer,":[55],"some":[56],"low-level":[57],"but":[58],"critical":[59],"for":[61],"concept":[62],"may":[64],"be":[65],"lost,":[66],"the":[68,113],"coupling":[69],"between":[70],"attribute":[71],"object":[73],"features":[74,86],"deepens.":[75],"To":[76],"address":[77],"these":[78],"issues,":[79],"we":[80],"propose":[81],"extract":[83],"multi-scale":[84,122],"fuse":[88],"them":[89],"in":[90,141],"an":[91],"adaptive":[92],"way":[93],"Mixture":[95],"of":[96],"Experts":[97],"(MoE)":[98],"networks.":[99],"We":[100],"also":[101],"employ":[102],"feature-level":[103],"similarity":[104],"a":[106],"maximum":[107],"entropy":[108],"regularization":[109],"term":[110],"constrain":[112],"model":[114],"effectively":[116],"disentangle":[117],"information.":[124],"Comprehensive":[125],"experiments":[126],"on":[127],"three":[128],"benchmark":[130],"datasets":[131],"demonstrate":[132],"that":[133],"our":[134],"method":[135],"significantly":[136],"outperforms":[137],"previous":[138],"SOTA":[139],"methods":[140],"both":[142],"closed-world":[143],"open-world":[145],"settings.":[146]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-12-06T00:00:00"}