{"id":"https://openalex.org/W4386596824","doi":"https://doi.org/10.1109/icip49359.2023.10223093","title":"Pyramid Masked Image Modeling for Transformer-Based Aerial Object Detection","display_name":"Pyramid Masked Image Modeling for Transformer-Based Aerial Object Detection","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386596824","doi":"https://doi.org/10.1109/icip49359.2023.10223093"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5101776528","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0003-2745-1656"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011105024","display_name":"Tianshan Liu","orcid":"https://orcid.org/0000-0003-3831-8893"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianshan Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086183661","display_name":"Yakun Ju","orcid":"https://orcid.org/0000-0003-4065-4108"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yakun Ju","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kin-Man Lam","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101776528"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.9781,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78024849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1675","last_page":"1679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.729679524898529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7097508907318115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6881349086761475},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.673340380191803},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6502234935760498},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6334744691848755},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.56695955991745},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4769493639469147},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43361347913742065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39018672704696655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3508302569389343},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3114888370037079},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11924254894256592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0700182318687439}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.729679524898529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097508907318115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6881349086761475},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.673340380191803},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6502234935760498},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6334744691848755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.56695955991745},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4769493639469147},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43361347913742065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39018672704696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3508302569389343},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3114888370037079},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11924254894256592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0700182318687439},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10223093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2108598243","https://openalex.org/W2512351403","https://openalex.org/W2565639579","https://openalex.org/W2910778976","https://openalex.org/W2963037989","https://openalex.org/W2969393175","https://openalex.org/W2992240579","https://openalex.org/W2995801068","https://openalex.org/W3009818596","https://openalex.org/W3012573144","https://openalex.org/W3015238515","https://openalex.org/W3091571193","https://openalex.org/W3094502228","https://openalex.org/W3131500599","https://openalex.org/W3134025014","https://openalex.org/W3134419943","https://openalex.org/W3138516171","https://openalex.org/W3141474321","https://openalex.org/W3147835263","https://openalex.org/W3170863103","https://openalex.org/W3170874841","https://openalex.org/W3176495987","https://openalex.org/W3195277359","https://openalex.org/W3201260569","https://openalex.org/W3201797941","https://openalex.org/W3205138221","https://openalex.org/W3209066630","https://openalex.org/W3209073849","https://openalex.org/W4200133092","https://openalex.org/W4214829639","https://openalex.org/W4226359564","https://openalex.org/W4281385110","https://openalex.org/W4297239163","https://openalex.org/W4308237323","https://openalex.org/W4308237773","https://openalex.org/W4312715802","https://openalex.org/W4312804579","https://openalex.org/W4313024097","https://openalex.org/W4313156423","https://openalex.org/W4313525589","https://openalex.org/W6788135285","https://openalex.org/W6796761347","https://openalex.org/W6838332116"],"related_works":["https://openalex.org/W4396860960","https://openalex.org/W4390482660","https://openalex.org/W2972256598","https://openalex.org/W2610408157","https://openalex.org/W4388813151","https://openalex.org/W2612465689","https://openalex.org/W4284972948","https://openalex.org/W4237245474","https://openalex.org/W2099047584","https://openalex.org/W4327521163"],"abstract_inverted_index":{"Two":[0],"obstacles,":[1],"the":[2,8,16,34,47,99],"scarcity":[3],"of":[4,18,26,103],"annotated":[5],"samples":[6],"and":[7,101],"difficulty":[9],"in":[10,70],"preserving":[11],"multi-scale":[12],"hierarchical":[13],"representations,":[14],"hinder":[15],"advancement":[17],"vision":[19],"Transformer-based":[20],"aerial":[21,71,90],"object":[22,91],"detection.":[23],"The":[24],"emergence":[25],"self-supervised":[27,68],"learning":[28],"has":[29],"inspired":[30],"some":[31],"solutions":[32,39],"to":[33,88],"first":[35],"issue.":[36,49],"However,":[37],"most":[38],"focus":[40],"on":[41],"single-scale":[42],"features,":[43],"conflicting":[44],"with":[45],"solving":[46],"second":[48],"To":[50],"bridge":[51],"this":[52,54],"gap,":[53],"paper":[55],"proposes":[56],"a":[57],"novel":[58],"pyramid":[59,79],"masked":[60],"image":[61],"modeling":[62],"(MIM)":[63],"framework,":[64],"termed":[65],"PyraMIM,":[66],"for":[67,93],"pretraining":[69],"scenarios.":[72],"Without":[73],"manual":[74],"annotation,":[75],"PyraMIM":[76],"enables":[77],"establishing":[78],"representations":[80],"during":[81],"pretraining,":[82],"which":[83],"can":[84],"be":[85],"seamlessly":[86],"adapted":[87],"downstream":[89],"detection":[92],"performance":[94],"improvement.":[95],"Experimental":[96],"results":[97],"demonstrate":[98],"effectiveness":[100],"superiority":[102],"our":[104],"method.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}