{"id":"https://openalex.org/W4402979744","doi":"https://doi.org/10.1109/icme57554.2024.10687693","title":"LDNET: Semantic Segmentation Of High-Resolution Images Via Learnable Patch Proposal And Dynamic Refinement","display_name":"LDNET: Semantic Segmentation Of High-Resolution Images Via Learnable Patch Proposal And Dynamic Refinement","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979744","doi":"https://doi.org/10.1109/icme57554.2024.10687693"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687693","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":"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/A5076826026","display_name":"Yuyang Ji","orcid":"https://orcid.org/0000-0003-0392-8261"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyang Ji","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010380116","display_name":"Lianlei Shan","orcid":"https://orcid.org/0000-0002-4648-8246"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianlei Shan","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.141,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97905419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.47690001130104065,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.47690001130104065,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/computer-science","display_name":"Computer science","score":0.7615005373954773},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7082855105400085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5934790372848511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802472829818726},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5659046769142151},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5304692983627319},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37004154920578003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615005373954773},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7082855105400085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5934790372848511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802472829818726},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5659046769142151},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5304692983627319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37004154920578003}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687693","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":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2563705555","https://openalex.org/W2565639579","https://openalex.org/W2609402060","https://openalex.org/W2787091153","https://openalex.org/W2804199516","https://openalex.org/W2886934227","https://openalex.org/W2946824094","https://openalex.org/W2955058313","https://openalex.org/W2963881378","https://openalex.org/W2964217532","https://openalex.org/W2998317038","https://openalex.org/W3034438741","https://openalex.org/W3089607830","https://openalex.org/W3162018314","https://openalex.org/W3172798612","https://openalex.org/W3197006556","https://openalex.org/W3205574222","https://openalex.org/W4224919078","https://openalex.org/W4312257162","https://openalex.org/W4312893741","https://openalex.org/W4385767482","https://openalex.org/W4386076151","https://openalex.org/W6631190155","https://openalex.org/W6717372056"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W1517180214","https://openalex.org/W4389858081","https://openalex.org/W2082780921","https://openalex.org/W2025517136","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Due":[0],"to":[1,19,25,85,91],"the":[2,27,34,74,80,87,157],"requirement":[3],"of":[4,10,36,63,68,82,141],"large":[5],"GPU":[6],"memory,":[7],"semantic":[8,61],"segmentation":[9,62],"ultra-high-resolution":[11],"images":[12],"faces":[13],"many":[14],"challenges.":[15],"Previous":[16],"methods":[17,160],"are":[18],"downsample":[20],"or":[21,39],"crop":[22],"into":[23,73],"patches":[24,72],"fit":[26],"GPU\u2019s":[28],"memory":[29],"limitations,":[30],"which":[31],"results":[32,148],"in":[33],"loss":[35],"detailed":[37],"information":[38],"context.":[40],"To":[41],"solve":[42],"this":[43,137],"problem,":[44],"we":[45,78,101],"propose":[46,102],"a":[47,103],"multi-branch":[48],"network":[49,75],"called":[50,105],"Learnable":[51],"Patch":[52],"Proposal":[53],"and":[54,118,125,166],"Dynamic":[55,106],"Refinement":[56],"Network":[57],"(LD-Net)":[58],"specifically":[59],"for":[60,76,99],"high-resolution":[64],"aerial":[65],"images.":[66],"Instead":[67],"simply":[69],"putting":[70],"all":[71],"fusion,":[77],"calculate":[79],"uncertainties":[81],"each":[83],"patch":[84],"select":[86],"most":[88],"valuable":[89],"ones":[90],"avoid":[92],"invalid":[93],"operations,":[94],"thus":[95],"improving":[96],"efficiency.":[97],"As":[98],"accuracy,":[100],"module":[104,109],"Refinement.":[107],"This":[108],"uses":[110],"global":[111],"features":[112,120,142],"(from":[113,121],"downsampling":[114],"images)":[115],"as":[116,123],"queries":[117],"local":[119],"patches)":[122],"keys":[124],"values":[126],"when":[127],"fusing":[128],"features.":[129],"Vice":[130],"versa":[131],"can":[132,143],"also":[133],"be":[134,144],"established.":[135],"In":[136],"way,":[138],"different":[139],"types":[140],"effectively":[145],"integrated.":[146],"Experimental":[147],"show":[149],"that":[150],"our":[151],"method":[152],"achieves":[153],"remarkable":[154],"improvements":[155],"over":[156],"previous":[158],"state-of-the-art":[159],"on":[161],"two":[162],"benchmark":[163],"datasets":[164],"DeepGlobe":[165],"ISIC.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}