{"id":"https://openalex.org/W4416649949","doi":"https://doi.org/10.1109/tgrs.2025.3636596","title":"Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning","display_name":"Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416649949","doi":"https://doi.org/10.1109/tgrs.2025.3636596"},"language":null,"primary_location":{"id":"doi:10.1109/tgrs.2025.3636596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3636596","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","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":null,"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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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/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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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/A5112491998","display_name":"Changhui Xu","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":"Changhui Xu","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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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","Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":"Ministry of Education of China, Key Laboratory of Intelligent Perception and Image Understanding, 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":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3286699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9890000224113464,"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":0.9890000224113464,"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":0.002199999988079071,"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":0.0019000000320374966,"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":0.8525000214576721},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6230999827384949},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5934000015258789},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3864000141620636},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3824000060558319},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.38119998574256897},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3625999987125397},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3352999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8575999736785889},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8525000214576721},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.6280999779701233},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42010000348091125},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3864000141620636},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3636596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3636596","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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"},{"id":"https://openalex.org/G8557548332","display_name":null,"funder_award_id":"2024CY2-GJHX-17","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2550553598","https://openalex.org/W2779054585","https://openalex.org/W2920981979","https://openalex.org/W2950635152","https://openalex.org/W2966926453","https://openalex.org/W2968831808","https://openalex.org/W2974212192","https://openalex.org/W2987228832","https://openalex.org/W3015625772","https://openalex.org/W3034655362","https://openalex.org/W3042724941","https://openalex.org/W3154766321","https://openalex.org/W3174377922","https://openalex.org/W4206028074","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4282968790","https://openalex.org/W4283216168","https://openalex.org/W4292968451","https://openalex.org/W4293508747","https://openalex.org/W4303444943","https://openalex.org/W4304092489","https://openalex.org/W4307430885","https://openalex.org/W4312289196","https://openalex.org/W4312390120","https://openalex.org/W4312712450","https://openalex.org/W4385245566","https://openalex.org/W4385864244","https://openalex.org/W4386003541","https://openalex.org/W4386076004","https://openalex.org/W4386162736","https://openalex.org/W4387546267","https://openalex.org/W4387986561","https://openalex.org/W4389091674","https://openalex.org/W4390873264","https://openalex.org/W4391305855","https://openalex.org/W4391341588","https://openalex.org/W4391594031","https://openalex.org/W4394585954","https://openalex.org/W4394804940","https://openalex.org/W4394938913","https://openalex.org/W4394966885","https://openalex.org/W4396941249","https://openalex.org/W4399294627","https://openalex.org/W4400977318","https://openalex.org/W4403183405","https://openalex.org/W4403864103","https://openalex.org/W4404040363","https://openalex.org/W4404563351","https://openalex.org/W4404809811","https://openalex.org/W4405521165","https://openalex.org/W4405844913","https://openalex.org/W4406114612","https://openalex.org/W4407637960","https://openalex.org/W4411408475","https://openalex.org/W4414153662"],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1,17,31,73,85,124,191],"image":[2,74,116,192],"captioning":[3,164,193],"between":[4],"visual":[5],"images":[6],"and":[7,24,45,177,197,202,205],"natural":[8],"language":[9],"remains":[10],"a":[11,63,104,138,163,170],"long-standing":[12],"challenge":[13],"in":[14,29,83],"the":[15,21,39,60,80,94,99,113,119,130,134,146,150,154,180,182,185,206,209,216],"remote":[16,30,72,84,123,190],"community.":[18],"Due":[19],"to":[20,36,53,77,92,110,127,144,168],"wide":[22],"coverage":[23],"large":[25],"amount":[26],"of":[27,122,133,149,184,208,218],"information":[28,42,82,132],"images,":[32,86],"existing":[33],"methods":[34],"struggle":[35],"effectively":[37],"utilize":[38],"relevant":[40,155],"semantic":[41,81,131,139,147],"about":[43],"objects":[44,176],"their":[46],"attributes":[47],"at":[48,227],"different":[49],"scales":[50],"across":[51],"samples":[52],"generate":[54,169],"descriptions.":[55],"To":[56],"address":[57],"these":[58],"issues,":[59],"article":[61],"proposes":[62],"novel":[64],"Adaptive":[65],"Scale-aware":[66],"Semantic":[67],"Memory":[68],"Network":[69],"(ASSMN)":[70],"for":[71],"captioning.":[75],"First,":[76],"fully":[78,128],"extract":[79],"multilevel":[87],"feature":[88,95],"enhancement":[89],"is":[90,108,142,166,195,212],"constructed":[91],"improve":[93],"representation":[96,148],"extracted":[97],"from":[98,158],"CLIP":[100],"pre-training":[101],"model.":[102],"Subsequently,":[103],"scale-aware":[105],"attention":[106],"aggregator":[107],"introduced":[109],"further":[111],"integrate":[112],"enhanced":[114],"multi-scale":[115],"features":[117],"into":[118],"high-level":[120],"semantics":[121,156],"images.":[125],"Then,":[126],"exploit":[129],"joint":[135],"observed":[136],"samples,":[137],"memory":[140],"reinforcement":[141],"designed":[143],"strengthen":[145],"current":[151],"scene":[152,172],"through":[153],"obtained":[157],"other":[159],"training":[160],"samples.":[161],"Finally,":[162],"decoder":[165],"performed":[167],"comprehensive":[171],"caption":[173],"with":[174,199],"accurate":[175],"attributes.":[178],"In":[179],"experiments,":[181],"performance":[183],"proposed":[186,210,220],"ASSMN":[187],"on":[188],"three":[189],"datasets":[194],"evaluated":[196],"compared":[198],"well-designed":[200],"baselines":[201],"state-of-the-art":[203],"methods,":[204],"superiority":[207],"method":[211],"demonstrated":[213],"by":[214],"ablating":[215],"role":[217],"each":[219],"component.":[221],"The":[222],"code":[223],"will":[224],"be":[225],"available":[226],"https://github.com/zcsisiyao/ASSMN.":[228]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-25T00:00:00"}