{"id":"https://openalex.org/W7163562646","doi":"https://doi.org/10.1145/3820057","title":"HTMA-CL: A Hierarchical Tokenization and Multiscale Attention Framework for Compressive Domain Multimedia Inference","display_name":"HTMA-CL: A Hierarchical Tokenization and Multiscale Attention Framework for Compressive Domain Multimedia Inference","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163562646","doi":"https://doi.org/10.1145/3820057"},"language":"en","primary_location":{"id":"doi:10.1145/3820057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820057","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3820057","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050578722","display_name":"Yanhao Jing","orcid":"https://orcid.org/0000-0001-5170-8744"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhao Jing","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0000-0001-5170-8744","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137895803","display_name":"Xiangjun Wu","orcid":"https://orcid.org/0000-0003-0371-8707"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjun Wu","raw_affiliation_strings":["School of Mathematics and Statistics, Henan University, Kaifeng, China and School of Computer and Information Engineering, Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0000-0003-0371-8707","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Henan University, Kaifeng, China and School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137862396","display_name":"Datao You","orcid":"https://orcid.org/0009-0009-9282-7024"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Datao You","raw_affiliation_strings":["School of Software, Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0009-0009-9282-7024","affiliations":[{"raw_affiliation_string":"School of Software, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010354178","display_name":"H B Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0009-0004-0685-9841","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137848903","display_name":"Zhe Hu","orcid":"https://orcid.org/0009-0006-4516-3219"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Hu","raw_affiliation_strings":["School of Mathematics and Statistics, Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0009-0006-4516-3219","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025009140","display_name":"Haibin Kan","orcid":"https://orcid.org/0000-0003-3062-5004"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Kan","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3062-5004","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103475155","display_name":"J urgen Kurths","orcid":null},"institutions":[{"id":"https://openalex.org/I60200437","display_name":"Potsdam Institute for Climate Impact Research","ror":"https://ror.org/03e8s1d88","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I60200437"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Kurths","raw_affiliation_strings":["Potsdam Institute for Climate Impact Research (PIK), Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5926-4276","affiliations":[{"raw_affiliation_string":"Potsdam Institute for Climate Impact Research (PIK), Potsdam, Germany","institution_ids":["https://openalex.org/I60200437"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63176764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"8","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.44690001010894775,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.44690001010894775,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.32359999418258667,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.026399999856948853,"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/inference","display_name":"Inference","score":0.6705999970436096},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5666000247001648},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.47600001096725464},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4165000021457672},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3695000112056732},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.930400013923645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4659000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4523000121116638},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4165000021457672},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3820057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820057","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3820057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820057","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2601955453","display_name":"\u57fa\u4e8e\u538b\u7f29\u611f\u77e5\u548c\u53d8\u6362\u57df\u7684\u6570\u5b57\u56fe\u50cf\u9690\u79c1\u4fdd\u62a4\u6280\u672f\u7814\u7a76","funder_award_id":"61872125","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4462146789","display_name":null,"funder_award_id":"2019-YFB2101703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1828462930","https://openalex.org/W2041101642","https://openalex.org/W2083993605","https://openalex.org/W2117539524","https://openalex.org/W2138863404","https://openalex.org/W2145096794","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2945467354","https://openalex.org/W2962858109","https://openalex.org/W3214466318","https://openalex.org/W4250955649","https://openalex.org/W4288054364","https://openalex.org/W4307842584","https://openalex.org/W4376607984","https://openalex.org/W4392157686","https://openalex.org/W4400340457"],"related_works":[],"abstract_inverted_index":{"Compressed":[0],"learning":[1,9],"(CL),":[2],"integrating":[3],"compressed":[4],"sensing":[5],"(CS)":[6],"and":[7,65,86,102,131,148],"machine":[8],"(ML),":[10],"enables":[11],"direct":[12],"inference":[13,110],"from":[14],"few":[15],"CS":[16,77,159],"measurements.":[17],"However,":[18],"existing":[19],"CL":[20,57,146],"methods":[21,156],"either":[22],"heavily":[23],"rely":[24],"on":[25,39],"pre-trained":[26],"models":[27,100],"built":[28],"upon":[29],"extremely":[30],"large-scale":[31],"datasets":[32],"or":[33],"perform":[34],"only":[35],"relatively":[36],"simple":[37],"tasks":[38,126],"small":[40],"datasets,":[41],"restricting":[42],"their":[43],"scalability":[44],"in":[45,112,173],"real-world":[46],"multimedia":[47,63,124,177],"scenarios.":[48],"To":[49],"address":[50],"these":[51],"limitations,":[52],"we":[53],"propose":[54],"an":[55],"efficient":[56],"framework":[58],"named":[59],"HTMA-CL":[60,69,139],"for":[61,78,121],"practical":[62],"acquisition":[64],"edge":[66],"intelligent":[67],"processing.":[68],"employs":[70],"CNN-based":[71],"learnable":[72],"sampling":[73],"to":[74,144,152],"realize":[75],"block-based":[76],"high-resolution":[79],"images,":[80],"significantly":[81],"decreasing":[82],"the":[83,106,113,153,167,174],"transmission":[84],"bandwidth":[85],"storage":[87],"overhead.":[88],"A":[89],"hierarchical":[90],"tokenization":[91],"module":[92,98],"together":[93],"with":[94],"a":[95,158],"deep-narrow":[96],"Transformer":[97],"progressively":[99],"local":[101],"global":[103],"dependencies":[104],"within":[105],"measurements,":[107],"enabling":[108],"accurate":[109],"directly":[111],"compressive":[114],"domain.":[115],"Various":[116],"task":[117],"heads":[118],"are":[119],"constructed":[120],"performing":[122],"diverse":[123],"analysis":[125],"such":[127],"as":[128],"image":[129,154],"classification":[130],"semantic":[132],"segmentation.":[133],"Extensive":[134],"experiments":[135],"demonstrate":[136],"that":[137],"our":[138],"achieves":[140],"state-of-the-art":[141],"performance":[142,151],"compared":[143],"other":[145],"methods,":[147],"nearly":[149],"comparable":[150],"domain":[155],"at":[157,185],"ratio":[160],"of":[161],"10%.":[162],"Our":[163],"method":[164],"further":[165],"verifies":[166],"strong":[168],"robustness":[169],"against":[170],"external":[171],"interference":[172],"disturbance-prone":[175],"IoT":[176],"environments.":[178],"The":[179],"source":[180],"code":[181],"is":[182],"publicly":[183],"available":[184],"https://github.com/acrlife/HTMA-CL.git":[186],".":[187]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-06-05T00:00:00"}