{"id":"https://openalex.org/W4415481167","doi":"https://doi.org/10.1109/jstars.2025.3624411","title":"HATNet: Hierarchical Attention Transformer With RS-CLIP Patch Tokens for Remote Sensing Image Captioning","display_name":"HATNet: Hierarchical Attention Transformer With RS-CLIP Patch Tokens for Remote Sensing Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415481167","doi":"https://doi.org/10.1109/jstars.2025.3624411"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2025.3624411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3624411","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/jstars.2025.3624411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049165403","display_name":"Zhongle Ren","orcid":"https://orcid.org/0000-0002-5425-6437"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongle Ren","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-5425-6437","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100918545","display_name":"Jianhua Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Meng","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026067746","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0002-0473-113X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0473-113X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062748878","display_name":"Shulin Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin Gao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-9787-9495","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043022387","display_name":"Biao Hou","orcid":"https://orcid.org/0000-0002-1996-186X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Hou","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1996-186X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008943930","display_name":"Weibin Li","orcid":"https://orcid.org/0000-0003-0047-8955"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Li","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-0047-8955","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058268359","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0003-4411-0933"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-4411-0933","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050630882","display_name":"Licheng Jiao","orcid":"https://orcid.org/0000-0003-3354-9617"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Jiao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3354-9617","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":0.5264,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68284649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":null,"first_page":"27208","last_page":"27223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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":0.9864000082015991,"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/closed-captioning","display_name":"Closed captioning","score":0.8981999754905701},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6868000030517578},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5533999800682068},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4027999937534332},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.391400009393692},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.37380000948905945},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37049999833106995},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.37049999833106995}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8981999754905701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665000200271606},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6868000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666999816894531},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2025.3624411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3624411","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8d9bf7eb15ab4d2386c9cfedcc577d2d","is_oa":true,"landing_page_url":"https://doaj.org/article/8d9bf7eb15ab4d2386c9cfedcc577d2d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 18, Pp 27208-27223 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2025.3624411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3624411","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1602717822","display_name":null,"funder_award_id":"62401418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1836536549","display_name":null,"funder_award_id":"62271377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G439018681","display_name":null,"funder_award_id":"62171347","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6432615666","display_name":null,"funder_award_id":"62371373","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1,18,115],"image":[2,57],"captioning":[3],"(RSIC)":[4],"aims":[5],"to":[6,77,82,88,119,133,147,168,178],"generate":[7],"natural":[8,66],"language":[9],"descriptions":[10,25],"of":[11,31],"critical":[12],"visual":[13,90,150],"content":[14],"in":[15,38],"overhead-view":[16],"remote":[17,114],"images.":[19],"However,":[20],"existing":[21],"methods":[22],"often":[23],"produce":[24],"with":[26,40,129,160],"significant":[27],"omissions":[28],"and":[29,44,72,92,137,162,170,191],"misidentifications":[30],"scene":[32],"types":[33],"or":[34,62],"object":[35],"counts,":[36],"particularly":[37],"scenes":[39],"complex":[41],"semantics(e.g.,school,":[42],"park)":[43],"images":[45,67],"containing":[46],"multiple":[47],"targets.":[48],"These":[49],"issues":[50],"stem":[51],"from":[52],"two":[53],"primary":[54],"limitations:":[55],"Pre-trained":[56],"encoders":[58],"such":[59],"as":[60],"ResNet":[61],"CLIP,":[63],"trained":[64],"on":[65,113,154,173],"for":[68],"classification,":[69],"exhibit":[70],"task":[71],"domain":[73],"mismatches":[74],"when":[75],"applied":[76],"RSIC;":[78],"Transformer-based":[79],"decoders":[80],"fail":[81],"effectively":[83],"align":[84],"cross-modal":[85,135],"features,":[86],"leading":[87],"underutilized":[89],"cues":[91],"semantic":[93],"inaccuracies.":[94],"To":[95],"address":[96],"these":[97],"challenges,":[98],"we":[99],"propose":[100],"HATNet,":[101],"a":[102,109,124,138],"novel":[103],"architecture":[104],"featuring":[105],"three":[106,155],"key":[107],"components:":[108],"Vision":[110],"Transformer":[111,127],"fine-tuned":[112],"image-text":[116],"pairs":[117],"(RS-CLIP)":[118],"extract":[120],"spatially-aware":[121],"patch":[122],"tokens;":[123],"hierarchical":[125],"attention":[126,131,201],"(HAT)":[128],"spatial-channel":[130],"mechanisms":[132],"refine":[134],"alignment;":[136],"pre-encoded":[139],"text":[140],"encoder":[141],"(PTE)":[142],"that":[143,185],"elevates":[144],"textual":[145],"features":[146],"match":[148],"high-level":[149],"semantics.":[151],"Extensive":[152],"experiments":[153],"benchmarks":[156],"demonstrate":[157],"state-of-the-art":[158],"performance,":[159],"CIDEr":[161],"BLEU-4":[163],"scores":[164],"improving":[165],"by":[166,189,195],"up":[167],"18.07%":[169],"5.88%,":[171],"respectively,":[172],"the":[174],"NWPU-Captions":[175],"dataset":[176],"compared":[177],"prior":[179],"methods.":[180],"Our":[181],"ablation":[182],"studies":[183],"validate":[184],"HATNet":[186],"mitigates":[187],"misidentification":[188],"69.6%":[190],"reduces":[192],"omission":[193],"errors":[194],"67.5%,":[196],"while":[197],"visualizations":[198],"confirm":[199],"improved":[200],"alignment.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-23T00:00:00"}