{"id":"https://openalex.org/W4412100034","doi":"https://doi.org/10.1145/3725949.3725958","title":"Transformer Based Remote Sensing Image Captioning with Object Count Information","display_name":"Transformer Based Remote Sensing Image Captioning with Object Count Information","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4412100034","doi":"https://doi.org/10.1145/3725949.3725958"},"language":"en","primary_location":{"id":"doi:10.1145/3725949.3725958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725958","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082169421","display_name":"Zihao Ni","orcid":"https://orcid.org/0000-0001-6056-6477"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Ni","raw_affiliation_strings":["China University of Petroleum (East China), Qingdao, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0001-6056-6477","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), Qingdao, Shandong, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525466","display_name":"Zhaoyun Zong","orcid":"https://orcid.org/0000-0002-6175-8451"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyun Zong","raw_affiliation_strings":["China University of Petroleum (East China), Qingdao, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-6175-8451","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), Qingdao, Shandong, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098670998","display_name":"Yinghao Xu","orcid":"https://orcid.org/0009-0003-2919-7142"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghao Xu","raw_affiliation_strings":["China University of Petroleum (East China), Qingdao, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0003-2919-7142","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), Qingdao, Shandong, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767704","display_name":"Peng Ren","orcid":"https://orcid.org/0000-0003-3949-985X"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Ren","raw_affiliation_strings":["China University of Petroleum (East China), Qingdao, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0003-3949-985X","affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), Qingdao, Shandong, China","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210162190"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37450117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"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":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9904000163078308,"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":0.8884289264678955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6749085187911987},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.610646665096283},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.5031539797782898},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4543842077255249},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4470665752887726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262653887271881},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4131265878677368},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.24748873710632324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1487044095993042},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09659740328788757}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8884289264678955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6749085187911987},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.610646665096283},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.5031539797782898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4543842077255249},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4470665752887726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262653887271881},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4131265878677368},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.24748873710632324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1487044095993042},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09659740328788757}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725949.3725958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725949.3725958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412100034.pdf","grobid_xml":"https://content.openalex.org/works/W4412100034.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2506483933","https://openalex.org/W2963084599","https://openalex.org/W3103911883","https://openalex.org/W3154766321","https://openalex.org/W3203553414","https://openalex.org/W3212381256","https://openalex.org/W4200272616","https://openalex.org/W4211112734","https://openalex.org/W4213449032","https://openalex.org/W4220716465","https://openalex.org/W4283216168","https://openalex.org/W4289654392","https://openalex.org/W4296280877","https://openalex.org/W4313021481","https://openalex.org/W4317433994","https://openalex.org/W4321617540","https://openalex.org/W4366123788","https://openalex.org/W4379279809","https://openalex.org/W4386076004","https://openalex.org/W4386127154","https://openalex.org/W4386460485","https://openalex.org/W4392151980","https://openalex.org/W4401754729"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,16,35,57,83,102,171],"image":[2,36,58,84,103,172],"captioning":[3,104],"is":[4,115],"a":[5,48],"task":[6,149],"that":[7,161],"aims":[8,107],"to":[9,19,29,51,90,108,147,182],"automatically":[10],"generate":[11],"descriptive":[12],"captions":[13,173],"for":[14],"remote":[15,56,82,101,170],"images,":[17],"helping":[18],"interpret":[20],"and":[21,68,143,180],"summarize":[22],"visual":[23],"content.Although":[24],"latest":[25],"works":[26],"are":[27],"able":[28],"reflect":[30],"fundermental":[31],"information":[32,41,80,114,179],"of":[33,76,94,150,154,169],"remoter":[34],"captions,":[37,120],"the":[38,74,88,92,118,124,148,152,167,192],"object":[39,53,78,112,177],"count":[40,54,79,113,178],"still":[42],"absence.In":[43],"this":[44],"paper,":[45],"we":[46,61,186],"propose":[47,62],"new":[49],"framework":[50,60,72,97,164],"incorporate":[52],"into":[55,117,156],"captions.The":[59,157],"contains":[63],"three":[64],"models:":[65],"Vis-Transformer,":[66],"Cap-Transformer":[67],"numeral":[69],"caption":[70,126],"generating.The":[71],"solves":[73],"problem":[75],"lacking":[77],"in":[81],"captions.We":[85],"set":[86],"up":[87],"experiment":[89,106],"evaluate":[91],"performance":[93],"our":[95,129,162,183],"proposed":[96,163],"on":[98,191],"several":[99],"widely-used":[100],"datasets.The":[105],"analyze":[109],"how":[110],"effectively":[111],"incorporated":[116],"generated":[119],"as":[121,123],"well":[122],"overall":[125],"quality.We":[127],"compare":[128],"method":[130],"with":[131],"state-of-the-art":[132],"models":[133],"across":[134],"multiple":[135],"metrics,":[136],"including":[137],"BLEU,":[138],"ROUGE,":[139],"CIDEr,":[140],"SPICE,":[141],"METEOR,":[142],"Num-Meteor.We":[144],"applied":[145],"Transformer":[146],"integrating":[151],"number":[153],"objects":[155],"experimental":[158],"results":[159,190],"indicate":[160],"significantly":[165],"improves":[166],"accuracy":[168],"by":[174],"successfully":[175],"incorporating":[176],"compared":[181],"previous":[184],"research,":[185],"have":[187],"achieved":[188],"better":[189],"RSICD":[193],"dataset.":[194]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}