{"id":"https://openalex.org/W4402979715","doi":"https://doi.org/10.1109/icme57554.2024.10688090","title":"HctMAE: Hybrid Convolution-Transformer Meets Masked Autoencoder for Plant Recognition","display_name":"HctMAE: Hybrid Convolution-Transformer Meets Masked Autoencoder for Plant Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979715","doi":"https://doi.org/10.1109/icme57554.2024.10688090"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688090","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5055752547","display_name":"Hongjing Su","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongjing Su","raw_affiliation_strings":["School of Information Science and Engineering Lanzhou University,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering Lanzhou University,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101243972","display_name":"Fuxiang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuxiang Lu","raw_affiliation_strings":["School of Information Science and Engineering Lanzhou University,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering Lanzhou University,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055752547"],"corresponding_institution_ids":["https://openalex.org/I76214153"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09219089,"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/T10616","display_name":"Smart Agriculture and AI","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7790811061859131},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6228530406951904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6014726161956787},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.48449084162712097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4505987763404846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4100651443004608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4073769152164459},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2598036229610443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21435043215751648},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17124897241592407},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09961807727813721}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7790811061859131},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6228530406951904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6014726161956787},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.48449084162712097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4505987763404846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4100651443004608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4073769152164459},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2598036229610443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21435043215751648},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17124897241592407},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09961807727813721}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688090","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.47999998927116394,"display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"Plant":[0],"recognition":[1],"plays":[2],"a":[3,70,79,94,109,130],"crucial":[4],"role":[5],"in":[6,18,38,99,115],"biodiversity":[7],"protection,":[8],"agricultural":[9],"food":[10],"security":[11],"and":[12,41,59,86,138],"etc.":[13],"Despite":[14],"recent":[15],"significant":[16,53],"success":[17],"convolutional":[19,83],"neural":[20,84],"network-related":[21],"works,":[22],"there":[23],"are":[24],"still":[25],"challenging":[26],"situations":[27],"to":[28,88,117],"address,":[29],"such":[30,65],"as":[31,50,52,74],"subtle":[32],"differences":[33],"between":[34],"similar":[35],"species,":[36,49],"diversity":[37],"size,":[39],"color,":[40],"texture":[42],"at":[43],"different":[44,120],"stages":[45],"of":[46,105],"the":[47,100,103,119,125],"same":[48],"well":[51],"noise":[54],"from":[55],"varying":[56],"lighting,":[57],"angles,":[58],"backgrounds":[60],"during":[61],"photography.":[62],"To":[63,123],"tackle":[64],"challenges,":[66],"this":[67],"paper":[68],"proposes":[69],"novel":[71],"network":[72],"named":[73],"HctMAE.":[75],"First,":[76],"HctMAE":[77,92,116,146],"utilizes":[78],"hybrid":[80],"encoder":[81],"with":[82],"networks":[85],"transformers":[87],"extract":[89],"features.":[90,107],"Then,":[91],"employs":[93],"dual-branch":[95],"information":[96],"aggregation":[97],"module":[98,112],"decoder":[101],"for":[102],"fusion":[104],"multiscale":[106],"Finally,":[108],"complementary":[110],"enhancement":[111],"is":[113],"used":[114],"fit":[118],"semantic":[121],"information.":[122],"evaluate":[124],"proposed":[126],"HctMAE,":[127],"we":[128],"collected":[129],"large":[131],"dataset,":[132],"LZU1226.":[133],"Extensive":[134],"experiments":[135],"on":[136],"LZU1226":[137],"other":[139],"publicly":[140],"available":[141],"plant":[142],"datasets":[143],"show":[144],"that":[145],"outperforms":[147],"most":[148],"state-of-the-art":[149],"algorithms.":[150]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}