{"id":"https://openalex.org/W4402258981","doi":"https://doi.org/10.1109/igarss53475.2024.10642778","title":"Remote Sensing Image Captioning With Multi-Scale Feature and Small Target Attention","display_name":"Remote Sensing Image Captioning With Multi-Scale Feature and Small Target Attention","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402258981","doi":"https://doi.org/10.1109/igarss53475.2024.10642778"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10642778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10642778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 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/A5045904147","display_name":"Kangda Cheng","orcid":"https://orcid.org/0000-0001-5525-6423"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangda Cheng","raw_affiliation_strings":["Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058198609","display_name":"Zhilu Wu","orcid":"https://orcid.org/0000-0002-3402-9093"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilu Wu","raw_affiliation_strings":["Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379980","display_name":"Haiyan Jin","orcid":"https://orcid.org/0009-0001-8745-3648"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyan Jin","raw_affiliation_strings":["Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101617347","display_name":"Xiaobao Li","orcid":"https://orcid.org/0000-0002-4088-0060"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobao Li","raw_affiliation_strings":["Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Electronics and Information Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7436","last_page":"7439"},"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":0.9995999932289124,"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":0.994700014591217,"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":0.9611020684242249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7470097541809082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7021147608757019},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.590738832950592},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5541620254516602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142042636871338},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5012373924255371},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4899372458457947},{"id":"https://openalex.org/keywords/feature-detection","display_name":"Feature detection (computer vision)","score":0.42831724882125854},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41204166412353516},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33462536334991455},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.20690858364105225},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1012030839920044},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08280137181282043}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9611020684242249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470097541809082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7021147608757019},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.590738832950592},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5541620254516602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142042636871338},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5012373924255371},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4899372458457947},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.42831724882125854},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41204166412353516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33462536334991455},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.20690858364105225},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1012030839920044},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08280137181282043},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10642778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10642778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2510520237","https://openalex.org/W2779054585","https://openalex.org/W2891444561","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2979924880","https://openalex.org/W2995904231","https://openalex.org/W3038038411","https://openalex.org/W3097754216","https://openalex.org/W3100245404","https://openalex.org/W4285156110"],"related_works":["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","https://openalex.org/W2077391823"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,19,106],"images":[2,107],"encompass":[3],"a":[4,33,60],"multitude":[5],"of":[6,43,55],"targets":[7],"with":[8,108],"varying":[9],"scales":[10],"and":[11,26,53,74,111],"lower":[12,109],"resolutions,":[13],"posing":[14],"significant":[15],"challenges":[16],"for":[17],"remote":[18,105],"image":[20,28],"captioning":[21],"tasks.":[22],"To":[23],"fully":[24],"extract":[25],"leverage":[27],"features,":[29],"this":[30],"paper":[31],"proposes":[32],"multi-scale":[34],"feature":[35],"extraction":[36],"network":[37],"that":[38,86],"enhances":[39],"the":[40,68,87,91],"representational":[41],"capacity":[42],"features":[44],"by":[45],"integrating":[46],"different":[47],"scales,":[48],"enabling":[49],"more":[50],"accurate":[51],"identification":[52],"description":[54],"targets.":[56,76,113],"Additionally,":[57],"we":[58],"designed":[59],"Small":[61],"Target":[62],"Attention":[63],"module":[64],"to":[65,71],"further":[66],"enhance":[67],"network\u2019s":[69],"sensitivity":[70],"densely":[72],"distributed":[73],"small-sized":[75,112],"Extensive":[77],"experiments":[78],"conducted":[79],"on":[80],"three":[81],"publicly":[82],"available":[83],"datasets":[84],"demonstrate":[85],"proposed":[88],"method":[89],"outperforms":[90],"compared":[92],"methods":[93],"in":[94],"capturing":[95],"key":[96],"information.":[97],"Moreover,":[98],"it":[99],"shows":[100],"better":[101],"performance":[102],"when":[103],"processing":[104],"resolutions":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}