{"id":"https://openalex.org/W4413553243","doi":"https://doi.org/10.1109/lgrs.2025.3602267","title":"Aerial Image Semantic Segmentation Method Based on Cross-Modal Hierarchical Feature Fusion","display_name":"Aerial Image Semantic Segmentation Method Based on Cross-Modal Hierarchical Feature Fusion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413553243","doi":"https://doi.org/10.1109/lgrs.2025.3602267"},"language":"en","primary_location":{"id":"doi:10.1109/lgrs.2025.3602267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3602267","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","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":"Jinglei Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglei Bai","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054433147","display_name":"Jinfu Yang","orcid":"https://orcid.org/0000-0002-1969-2161"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfu Yang","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1969-2161","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Xiang","orcid":"https://orcid.org/0009-0006-8406-7561"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xiang","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8406-7561","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110368101","display_name":"Shu Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Cai","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-9857-7884","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17342542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9104999899864197,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9104999899864197,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.9077000021934509,"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/T12983","display_name":"Satellite Image Processing and Photogrammetry","score":0.9071000218391418,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7124371528625488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.708156406879425},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6110363602638245},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5923013687133789},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5796132683753967},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5777419805526733},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5601210594177246},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4978675842285156},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.47864830493927},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47435462474823},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4316655993461609},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4178262948989868},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40793466567993164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124371528625488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.708156406879425},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6110363602638245},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5923013687133789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5796132683753967},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5777419805526733},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5601210594177246},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4978675842285156},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.47864830493927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47435462474823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4316655993461609},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4178262948989868},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40793466567993164},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/lgrs.2025.3602267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3602267","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3535677879","display_name":null,"funder_award_id":"2024Z071075001","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2560023338","https://openalex.org/W3007268491","https://openalex.org/W3108601100","https://openalex.org/W3127751679","https://openalex.org/W3137572916","https://openalex.org/W3202370946","https://openalex.org/W3207537403","https://openalex.org/W4224937906","https://openalex.org/W4229058281","https://openalex.org/W4283450732","https://openalex.org/W4386179772","https://openalex.org/W4387618979","https://openalex.org/W4389665312","https://openalex.org/W4392543906","https://openalex.org/W4393397443","https://openalex.org/W4401567734","https://openalex.org/W4402716243","https://openalex.org/W4402904020","https://openalex.org/W4402916520","https://openalex.org/W4407690759","https://openalex.org/W4408467392","https://openalex.org/W4408703259"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272","https://openalex.org/W1989561795"],"abstract_inverted_index":{"Multimodal":[0],"aerial":[1],"image":[2],"semantic":[3],"segmentation":[4],"enables":[5],"fine-grained":[6],"land":[7],"cover":[8],"classification":[9],"by":[10,20],"integrating":[11],"data":[12],"from":[13],"different":[14],"sensors,":[15],"yet":[16],"it":[17],"remains":[18],"challenged":[19],"information":[21],"redundancy,":[22],"inter-modal":[23],"feature":[24,83],"discrepancies,":[25],"and":[26,59,69,74,90,98,110],"class":[27,92],"confusion":[28],"in":[29],"complex":[30],"scenes.":[31],"To":[32],"address":[33],"these":[34],"issues,":[35],"we":[36],"propose":[37],"a":[38,53,60,80],"Cross-Modal":[39],"Hierarchical":[40],"Feature":[41],"Fusion":[42,56,63],"Network":[43],"(CMHFNet)":[44],"based":[45],"on":[46,95],"an":[47],"encoder-decoder":[48],"architecture.":[49],"The":[50,77],"encoder":[51],"incorporates":[52],"Pixel-wise":[54],"Attention-guided":[55],"Module":[57],"(PAFM)":[58],"Multi-stage":[61],"Progressive":[62],"Transformer":[64],"(MPFT)":[65],"to":[66,86],"suppress":[67],"redundancy":[68],"model":[70],"long-range":[71],"intermodal":[72],"dependencies":[73],"scale":[75],"variations.":[76],"decoder":[78],"introduces":[79],"residual":[81],"information-guided":[82],"compensation":[84],"mechanism":[85],"recover":[87],"spatial":[88],"details":[89],"mitigate":[91],"ambiguity.":[93],"Experiments":[94],"DDOS,":[96],"Vaihingen,":[97],"Potsdam":[99],"datasets":[100],"demonstrate":[101],"that":[102],"CMHFNet":[103],"surpasses":[104],"state-of-the-art":[105],"methods,":[106],"validating":[107],"its":[108],"effectiveness":[109],"practical":[111],"value.":[112]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}