{"id":"https://openalex.org/W4394653171","doi":"https://doi.org/10.1109/tgrs.2024.3392778","title":"Panoptic Perception: A Novel Task and Fine-Grained Dataset for Universal Remote Sensing Image Interpretation","display_name":"Panoptic Perception: A Novel Task and Fine-Grained Dataset for Universal Remote Sensing Image Interpretation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394653171","doi":"https://doi.org/10.1109/tgrs.2024.3392778"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3392778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3392778","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.04608","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036886150","display_name":"Danpei Zhao","orcid":"https://orcid.org/0000-0001-6701-0471"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danpei Zhao","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0001-7723-4823"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqiang Chen","orcid":"https://orcid.org/0000-0002-1648-6928"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Chen","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Li","orcid":"https://orcid.org/0000-0002-7318-5881"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Li","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuoran Liu","orcid":"https://orcid.org/0009-0003-7006-187X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Liu","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451406","display_name":"Wentao Li","orcid":"https://orcid.org/0000-0002-5367-3482"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Li","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yue Gao","orcid":"https://orcid.org/0000-0002-5020-586X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Gao","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036886150"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.681,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90980775,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.826524019241333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209967017173767},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7100555300712585},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6294205188751221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6049945950508118},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6018497347831726},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.49622946977615356},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.47549471259117126},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44340765476226807},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4047369658946991},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3897694945335388},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33510154485702515},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3192446827888489}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.826524019241333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209967017173767},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7100555300712585},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6294205188751221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049945950508118},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6018497347831726},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.49622946977615356},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.47549471259117126},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44340765476226807},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4047369658946991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3897694945335388},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33510154485702515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3192446827888489},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgrs.2024.3392778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3392778","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2404.04608","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.04608","pdf_url":"https://arxiv.org/pdf/2404.04608","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.04608","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.04608","pdf_url":"https://arxiv.org/pdf/2404.04608","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3221306437","display_name":null,"funder_award_id":"62271018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394653171.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1980038761","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2110764733","https://openalex.org/W2168809519","https://openalex.org/W2194775991","https://openalex.org/W2515866431","https://openalex.org/W2594177559","https://openalex.org/W2734349601","https://openalex.org/W2769613401","https://openalex.org/W2779054585","https://openalex.org/W2811199523","https://openalex.org/W2884419823","https://openalex.org/W2898504016","https://openalex.org/W2910628332","https://openalex.org/W2962749812","https://openalex.org/W2964257316","https://openalex.org/W2983342848","https://openalex.org/W2983717970","https://openalex.org/W2992240579","https://openalex.org/W2999219213","https://openalex.org/W3027225766","https://openalex.org/W3096609285","https://openalex.org/W3110908156","https://openalex.org/W3126404438","https://openalex.org/W3175205795","https://openalex.org/W3185151088","https://openalex.org/W4211112734","https://openalex.org/W4213229165","https://openalex.org/W4226456028","https://openalex.org/W4288325606","https://openalex.org/W4300479382","https://openalex.org/W4312815172","https://openalex.org/W4322706842","https://openalex.org/W4362654047","https://openalex.org/W4366377620","https://openalex.org/W4385245566","https://openalex.org/W4386384156","https://openalex.org/W4389610328","https://openalex.org/W4389776880","https://openalex.org/W4390874575","https://openalex.org/W4391331851","https://openalex.org/W4394698978","https://openalex.org/W6748130322","https://openalex.org/W6763251565","https://openalex.org/W6786609286","https://openalex.org/W6798837711","https://openalex.org/W6799579066","https://openalex.org/W6850787431","https://openalex.org/W6852909635"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Current":[0],"remote-sensing":[1],"interpretation":[2,28,39,64],"models":[3,20],"often":[4],"focus":[5],"on":[6,180,198],"a":[7,48,52,59,172],"single":[8],"task":[9,50,122,189],"such":[10],"as":[11],"detection,":[12],"segmentation,":[13,131,134],"or":[14],"caption.":[15],"However,":[16],"the":[17,25,116,124,141,183,186,191],"task-specific":[18],"designed":[19],"are":[21],"unattainable":[22],"to":[23,57,87,102,155],"achieve":[24,58],"comprehensive":[26],"multi-level":[27],"of":[29,118,127,185,194],"images.":[30],"The":[31,67,201],"field":[32],"also":[33],"lacks":[34],"support":[35],"for":[36,65,77,165],"multi-task":[37,109,113,195],"joint":[38,173,196],"datasets.":[40],"In":[41],"this":[42,121],"paper,":[43],"we":[44,170],"propose":[45,171],"Panoptic":[46],"Perception:":[47],"novel":[49],"and":[51,62,74,94,96,104,115,135,160,190],"new":[53,68],"fine-grained":[54,128,137,150],"dataset":[55,143,202],"(FineGrip)":[56],"more":[60],"thorough":[61],"universal":[63,78],"RSIs.":[66],"task:":[69],"1)":[70],"integrates":[71],"pixel-level,":[72],"instance-level,":[73],"image-level":[75],"information":[76,84],"image":[79,83,138],"perception,":[80],"2)":[81],"captures":[82],"from":[85],"coarse":[86],"fine":[88],"granularity,":[89],"achieving":[90],"deeper":[91],"scene":[92],"understanding":[93],"description,":[95],"3)":[97],"enables":[98,123],"various":[99],"independent":[100],"tasks":[101],"complement":[103],"enhance":[105],"each":[106],"other":[107],"through":[108],"learning.":[110],"By":[111],"emphasizing":[112],"interactions":[114],"consistency":[117],"perception":[119,176,188],"results,":[120],"simultaneous":[125],"processing":[126],"foreground":[129,157],"instance":[130,151],"background":[132,162],"semantic":[133,163],"global":[136],"captioning.":[139],"Concretely,":[140],"FineGrip":[142,181],"includes":[144],"2,649":[145],"remote":[146],"sensing":[147],"images,":[148],"12054":[149],"segmentation":[152],"masks":[153,164],"belonging":[154],"20":[156],"things":[158],"categories,":[159],"7599":[161],"5":[166],"stuff":[167],"classes.":[168],"Furthermore,":[169],"optimization-based":[174],"panoptic":[175,187],"model.":[177],"Experimental":[178],"results":[179],"demonstrate":[182],"feasibility":[184],"beneficial":[192],"effect":[193],"optimization":[197],"individual":[199],"tasks.":[200],"will":[203],"be":[204],"publicly":[205],"available.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}