{"id":"https://openalex.org/W7140316647","doi":"https://doi.org/10.1109/icme59968.2025.11450318","title":"Puzzle-MAE: A Puzzle-Inspired Mask Autoencoder for Multi-Modal Fusion","display_name":"Puzzle-MAE: A Puzzle-Inspired Mask Autoencoder for Multi-Modal Fusion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7140316647","doi":"https://doi.org/10.1109/icme59968.2025.11450318"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11450318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11450318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5130560415","display_name":"Xin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["School of Intelligence Science and Technology, University of Science and Technology Beijing,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045750357","display_name":"Bochao Zou","orcid":"https://orcid.org/0000-0002-2126-8159"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bochao Zou","raw_affiliation_strings":["School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850312","display_name":"Rongquan Wang","orcid":"https://orcid.org/0000-0002-3375-9561"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongquan Wang","raw_affiliation_strings":["School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130591612","display_name":"Huimin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Ma","raw_affiliation_strings":["School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70778919,"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":"6"},"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":0.7487000226974487,"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":0.7487000226974487,"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":0.04500000178813934,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.531000018119812},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4959000051021576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.36059999465942383},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6578999757766724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583000183105469},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.531000018119812},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4821000099182129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23970000445842743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11450318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11450318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0],"unsupervised":[1],"methods":[2],"in":[3,14],"the":[4,17,26,63,74,81,117,131],"video":[5],"domain":[6],"rely":[7],"on":[8,127],"simple":[9],"encoder-decoder":[10],"structures,":[11],"often":[12],"resulting":[13],"discrepancies":[15],"between":[16],"features":[18,43],"extracted":[19],"from":[20,25,44],"unmasked":[21,48],"patches":[22,49],"and":[23,47,50,73,102,110,135],"those":[24],"original":[27,54],"patches.":[28],"To":[29],"address":[30],"this":[31],"issue,":[32],"we":[33,79,96],"propose":[34,80],"a":[35],"novel":[36],"self-supervised":[37],"learning":[38],"framework,":[39],"PuzzleMAE,":[40],"which":[41,85],"extracts":[42],"both":[45],"masked":[46],"aligns":[51],"them":[52],"with":[53,91],"image":[55,71],"representations":[56],"to":[57,66,106],"improve":[58],"feature":[59,93],"consistency.":[60],"Inspired":[61],"by":[62],"human":[64],"ability":[65],"solve":[67],"puzzles":[68],"through":[69],"holistic":[70],"recognition":[72],"exploitation":[75],"of":[76,113,122],"spatial":[77,109],"adjacency,":[78],"Global-Local":[82],"Attention":[83],"Module,":[84],"effectively":[86],"integrates":[87],"global":[88],"contextual":[89],"information":[90],"local":[92],"representations.":[94],"Furthermore,":[95],"introduce":[97],"3D":[98],"Relative":[99],"Position":[100,104],"Embedding":[101,105],"Structural":[103],"emulate":[107],"human-like":[108],"structural":[111],"awareness":[112],"positional":[114],"relationships":[115],"during":[116],"puzzle-solving":[118],"process.":[119],"The":[120],"effectiveness":[121],"our":[123],"method":[124],"is":[125],"validated":[126],"two":[128],"downstream":[129],"tasks:":[130],"First":[132],"Impression":[133],"V2":[134],"DFEW":[136],"datasets.":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-26T00:00:00"}