{"id":"https://openalex.org/W4317433994","doi":"https://doi.org/10.3390/rs15030579","title":"Multi-Source Interactive Stair Attention for Remote Sensing Image Captioning","display_name":"Multi-Source Interactive Stair Attention for Remote Sensing Image Captioning","publication_year":2023,"publication_date":"2023-01-18","ids":{"openalex":"https://openalex.org/W4317433994","doi":"https://doi.org/10.3390/rs15030579"},"language":"en","primary_location":{"id":"doi:10.3390/rs15030579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15030579","pdf_url":"https://www.mdpi.com/2072-4292/15/3/579/pdf?version=1674031585","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/15/3/579/pdf?version=1674031585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049776440","display_name":"Xiangrong Zhang","orcid":"https://orcid.org/0000-0003-0379-2042"},"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":"Xiangrong Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331846","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0002-6908-8966"},"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":"Yunpeng Li","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328100","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-2605-5504"},"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":"Xin Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523650","display_name":"Feixiang Liu","orcid":"https://orcid.org/0000-0001-9882-9439"},"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":"Feixiang Liu","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050091223","display_name":"Zhaoji Wu","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":"Zhaoji Wu","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007867868","display_name":"Xina Cheng","orcid":"https://orcid.org/0000-0001-7319-1635"},"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":true,"raw_author_name":"Xina Cheng","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050630882","display_name":"Licheng Jiao","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":"Licheng Jiao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5007867868"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":3.1065,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93180988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"579","last_page":"579"},"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":0.9970999956130981,"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":0.9940999746322632,"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":0.8916351795196533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8548734188079834},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5851520895957947},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5481141805648804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5350314974784851},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5258898138999939},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4279007017612457},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4196247458457947},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4155384302139282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34246116876602173},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0997452437877655}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8916351795196533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8548734188079834},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5851520895957947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5481141805648804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350314974784851},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5258898138999939},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4279007017612457},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4196247458457947},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4155384302139282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34246116876602173},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0997452437877655},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/rs15030579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15030579","pdf_url":"https://www.mdpi.com/2072-4292/15/3/579/pdf?version=1674031585","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5430dbef5a344c71aae07f3e0d1c2736","is_oa":true,"landing_page_url":"https://doaj.org/article/5430dbef5a344c71aae07f3e0d1c2736","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 15, Iss 3, p 579 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2072-4292/15/3/579/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/rs15030579","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing; Volume 15; Issue 3; Pages: 579","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/rs15030579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15030579","pdf_url":"https://www.mdpi.com/2072-4292/15/3/579/pdf?version=1674031585","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1147961060","display_name":null,"funder_award_id":"62276197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2470288359","display_name":null,"funder_award_id":"2019ZDLGY03-08","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5324547038","display_name":null,"funder_award_id":"62171332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5584298476","display_name":null,"funder_award_id":"62006178","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4317433994.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1849277567","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2086866337","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2144499799","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2510520237","https://openalex.org/W2538244214","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2552955500","https://openalex.org/W2560920409","https://openalex.org/W2575842049","https://openalex.org/W2603566245","https://openalex.org/W2613718673","https://openalex.org/W2620858446","https://openalex.org/W2733535455","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2783165089","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2955117135","https://openalex.org/W2963084599","https://openalex.org/W2964018924","https://openalex.org/W2964073694","https://openalex.org/W2979924880","https://openalex.org/W2995904231","https://openalex.org/W3011916860","https://openalex.org/W3017628311","https://openalex.org/W3034427230","https://openalex.org/W3034858767","https://openalex.org/W3046260628","https://openalex.org/W3100245404","https://openalex.org/W3111390112","https://openalex.org/W3119689583","https://openalex.org/W3157772069","https://openalex.org/W3168495321","https://openalex.org/W3194015448","https://openalex.org/W3200654829","https://openalex.org/W4213449032","https://openalex.org/W4214587440","https://openalex.org/W4283216168","https://openalex.org/W4385245566","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6800139171"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"The":[0,137],"aim":[1],"of":[2,49,98,104,181,202,211],"remote":[3,13],"sensing":[4,14],"image":[5,15],"captioning":[6],"(RSIC)":[7],"is":[8,173],"to":[9,124,177],"describe":[10],"a":[11,34,87,168],"given":[12],"(RSI)":[16],"using":[17],"coherent":[18],"sentences.":[19,39,184],"Most":[20],"existing":[21],"attention-based":[22],"methods":[23,42],"model":[24,205],"the":[25,47,54,58,62,96,107,126,141,148,151,160,179,182,192,200,203],"coherence":[26],"through":[27,46],"an":[28,118],"LSTM-based":[29],"decoder,":[30],"which":[31,130],"dynamically":[32],"infers":[33],"word":[35,63,128],"vector":[36,64],"from":[37,65],"preceding":[38,99],"However,":[40],"these":[41],"are":[43,73,163],"indirectly":[44],"guided":[45],"confusion":[48],"attentive":[50,142],"regions,":[51],"as":[52,114],"(1)":[53],"weighted":[55],"average":[56],"in":[57,159,175,209],"attention":[59,91,119,139],"mechanism":[60,92,120],"distracts":[61],"capturing":[66],"pertinent":[67],"visual":[68,102],"regions":[69,103,158],"and":[70,101,116,154,195],"(2)":[71],"there":[72],"few":[74],"constraints":[75],"or":[76],"rewards":[77],"for":[78],"learning":[79,172],"long-range":[80],"transitions.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"multi-source":[88,108],"interactive":[89],"stair":[90,138],"that":[93],"separately":[94],"models":[95],"semantics":[97],"sentences":[100],"interest.":[105],"Specifically,":[106],"interaction":[109],"takes":[110],"previous":[111],"semantic":[112],"vectors":[113],"queries":[115],"applies":[117],"on":[121,165,187],"regional":[122],"features":[123],"acquire":[125],"next":[127],"vector,":[129],"reduces":[131],"immediate":[132],"hesitation":[133],"by":[134],"considering":[135],"linguistics.":[136],"divides":[140],"weights":[143],"into":[144],"three":[145],"levels\u2014that":[146],"is,":[147],"core":[149],"region,":[150,153],"surrounding":[152],"other":[155],"regions\u2014and":[156],"all":[157],"search":[161],"scope":[162],"focused":[164],"differently.":[166],"Then,":[167],"CIDEr-based":[169],"reward":[170],"reinforcement":[171],"devised,":[174],"order":[176],"enhance":[178],"quality":[180],"generated":[183],"Comprehensive":[185],"experiments":[186],"widely":[188],"used":[189],"benchmarks":[190],"(i.e.,":[191],"Sydney-Captions,":[193],"UCM-Captions,":[194],"RSICD":[196],"data":[197],"sets)":[198],"demonstrate":[199],"superiority":[201],"proposed":[204],"over":[206],"state-of-the-art":[207],"models,":[208],"terms":[210],"its":[212],"coherence,":[213],"while":[214],"maintaining":[215],"high":[216],"accuracy.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}