{"id":"https://openalex.org/W3130184989","doi":"https://doi.org/10.1109/igarss39084.2020.9323213","title":"Instance-Aware Remote Sensing Image Captioning with Cross-Hierarchy Attention","display_name":"Instance-Aware Remote Sensing Image Captioning with Cross-Hierarchy Attention","publication_year":2020,"publication_date":"2020-09-26","ids":{"openalex":"https://openalex.org/W3130184989","doi":"https://doi.org/10.1109/igarss39084.2020.9323213","mag":"3130184989"},"language":"en","primary_location":{"id":"doi:10.1109/igarss39084.2020.9323213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss39084.2020.9323213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","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/A5086326894","display_name":"Chengze Wang","orcid":"https://orcid.org/0000-0003-2349-6427"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengze Wang","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014401391","display_name":"Zhiyu Jiang","orcid":"https://orcid.org/0000-0002-6360-8262"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Jiang","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334733","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0001-7964-6514"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University,Xi'an,Shaanxi,P. R. China,710072","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.8543,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.82134449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.8464652299880981},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8435150384902954},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7169443368911743},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6503636240959167},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6333954334259033},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6292387843132019},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.611910879611969},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5786281824111938},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5224503874778748},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.43318700790405273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319911003112793},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.42171230912208557},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3280009627342224},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1595764458179474},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0812402069568634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464652299880981},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8435150384902954},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7169443368911743},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6503636240959167},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6333954334259033},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6292387843132019},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.611910879611969},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5786281824111938},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5224503874778748},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.43318700790405273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319911003112793},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.42171230912208557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3280009627342224},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1595764458179474},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0812402069568634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss39084.2020.9323213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss39084.2020.9323213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G11847706","display_name":null,"funder_award_id":"61632018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G331486752","display_name":null,"funder_award_id":"B16039","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1687846465","https://openalex.org/W1895577753","https://openalex.org/W2109586012","https://openalex.org/W2510520237","https://openalex.org/W2613718673","https://openalex.org/W2779054585","https://openalex.org/W2920981979","https://openalex.org/W2963084599","https://openalex.org/W2986534680","https://openalex.org/W3100245404","https://openalex.org/W6630875275","https://openalex.org/W6637306801","https://openalex.org/W6676497082"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4387969122","https://openalex.org/W4390871823"],"abstract_inverted_index":{"The":[0,98,152],"spatial":[1,18,57],"attention":[2,19,24,58,131],"is":[3,69,101,133],"a":[4,86,105,129],"straightforward":[5],"approach":[6,163],"to":[7,135,139],"enhance":[8],"the":[9,23,33,45,51,60,73,111,137,159],"performance":[10],"for":[11,71],"remote":[12,77,87],"sensing":[13,78,88],"image":[14,61,89],"captioning.":[15],"However,":[16],"conventional":[17,56],"approaches":[20],"consider":[21],"only":[22],"distribution":[25],"on":[26,124,142,155],"one":[27],"fixed":[28,52],"coarse":[29],"grid,":[30],"resulting":[31],"in":[32,63,76],"semantics":[34],"of":[35,55,114,161],"tiny":[36],"objects":[37],"can":[38],"be":[39],"easily":[40],"ignored":[41],"or":[42],"disturbed":[43],"during":[44],"visual":[46,112],"feature":[47,107,127],"extraction.":[48],"Worse":[49],"still,":[50],"semantic":[53,144],"level":[54],"limits":[59],"understanding":[62],"different":[64,143],"levels":[65],"and":[66,94,118,146],"perspectives,":[67],"which":[68],"critical":[70],"tackling":[72],"huge":[74],"diversity":[75],"images.":[79],"To":[80],"address":[81],"these":[82],"issues,":[83],"we":[84],"propose":[85],"caption":[90],"generator":[91],"with":[92],"instance-awareness":[93],"cross-hierarchy":[95,130],"attention.":[96],"1)":[97],"instances":[99,147],"awareness":[100],"achieved":[102],"by":[103],"introducing":[104],"multi-level":[106,115,126],"architecture":[108],"that":[109],"contains":[110],"information":[113],"instance-possible":[116],"regions":[117],"their":[119],"surroundings.":[120],"2)":[121],"Moreover,":[122],"based":[123],"this":[125],"extraction,":[128],"mechanism":[132],"proposed":[134,162],"prompt":[136],"decoder":[138],"dynamically":[140],"focus":[141],"hierarchies":[145],"at":[148],"each":[149],"time":[150],"step.":[151],"experimental":[153],"results":[154],"public":[156],"datasets":[157],"demonstrate":[158],"superiority":[160],"over":[164],"existing":[165],"methods.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}