{"id":"https://openalex.org/W7169677523","doi":"https://doi.org/10.1007/978-981-92-3520-9_49","title":"SASE-DETR: An Infrared Small and Dim Target Detection Method Integrating Spatially Adaptive Sampling and Semantic Enhancement","display_name":"SASE-DETR: An Infrared Small and Dim Target Detection Method Integrating Spatially Adaptive Sampling and Semantic Enhancement","publication_year":2026,"publication_date":"2026-07-18","ids":{"openalex":"https://openalex.org/W7169677523","doi":"https://doi.org/10.1007/978-981-92-3520-9_49"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3520-9_49","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_49","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_49.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_49.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100610626","display_name":"Shang Zhang","orcid":"https://orcid.org/0000-0002-4045-714X"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang Zhang","raw_affiliation_strings":["College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","institution_ids":["https://openalex.org/I161350542"]},{"raw_affiliation_string":"Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141129112","display_name":"Huipan Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huipan Guan","raw_affiliation_strings":["College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","institution_ids":["https://openalex.org/I161350542"]},{"raw_affiliation_string":"Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054408684","display_name":"Xiaobo Ding","orcid":"https://orcid.org/0000-0001-8902-7207"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Ding","raw_affiliation_strings":["College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","institution_ids":["https://openalex.org/I161350542"]},{"raw_affiliation_string":"Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101998250","display_name":"Guoqiang Gong","orcid":"https://orcid.org/0000-0003-2622-9092"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Gong","raw_affiliation_strings":["College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Technology, China Three Gorges University, Yichang, 443002, Hubei, China","institution_ids":["https://openalex.org/I161350542"]},{"raw_affiliation_string":"Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University, Yichang, 443002, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081045947","display_name":"Shentao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]},{"id":"https://openalex.org/I4210117020","display_name":"Nantong Science and Technology Bureau","ror":"https://ror.org/02tx34m84","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210117020"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shentao Wang","raw_affiliation_strings":["School of Yonyou Digital and Intelligence, Nantong Institute of Technology, Nantong, 226001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Yonyou Digital and Intelligence, Nantong Institute of Technology, Nantong, 226001, China","institution_ids":["https://openalex.org/I199305430","https://openalex.org/I4210117020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081045947"],"corresponding_institution_ids":["https://openalex.org/I199305430","https://openalex.org/I4210117020"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6337000131607056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6205000281333923},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5613999962806702},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5260000228881836},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.499099999666214},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45719999074935913},{"id":"https://openalex.org/keywords/infrared","display_name":"Infrared","score":0.4361000061035156},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.41679999232292175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676800012588501},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6337000131607056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5613999962806702},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45719999074935913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4377000033855438},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3847000002861023},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2984335091","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Thermal infrared","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3520-9_49","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_49","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_49.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-981-92-3520-9_49","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_49","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_49.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7169677523.pdf","grobid_xml":"https://content.openalex.org/works/W7169677523.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2080197848","https://openalex.org/W2144506857","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2601564443","https://openalex.org/W2738760021","https://openalex.org/W2953583213","https://openalex.org/W2963037989","https://openalex.org/W2963857746","https://openalex.org/W3096609285","https://openalex.org/W4214627427","https://openalex.org/W4214819464","https://openalex.org/W4313065862","https://openalex.org/W4402733568","https://openalex.org/W4402754006"],"related_works":[],"abstract_inverted_index":{"Infrared":[0],"small":[1,82,188],"and":[2,19,71,97,124,133,146,183],"dim":[3],"target":[4,13,189],"detection":[5,28,179],"is":[6,62,90,110],"highly":[7],"sensitive":[8],"to":[9,76,92,112],"background":[10],"clutter":[11],"because":[12],"responses":[14,80],"are":[15,74],"usually":[16],"weak,":[17],"sparse,":[18],"easily":[20],"confused":[21],"with":[22,136],"non-target":[23],"thermal":[24],"structures.":[25],"To":[26],"improve":[27],"robustness":[29],"under":[30,164],"complex":[31],"infrared":[32,166,187],"scenes":[33],"while":[34],"maintaining":[35],"computational":[36],"efficiency,":[37],"this":[38],"paper":[39],"presents":[40],"SASE-DETR,":[41],"an":[42,148],"improved":[43],"end-to-end":[44],"detector":[45],"built":[46],"on":[47,122,157],"RT-DETR.":[48],"The":[49],"proposed":[50,141],"framework":[51],"enhances":[52],"feature":[53,95,114],"representation":[54],"at":[55],"three":[56],"levels.":[57],"First,":[58],"a":[59,85,105,175],"C2f-SASCG":[60],"module":[61],"introduced":[63],"into":[64],"the":[65,99,140],"backbone,":[66],"where":[67],"spatially":[68],"adaptive":[69],"sampling":[70],"channel":[72],"gating":[73],"combined":[75],"strengthen":[77],"local":[78],"structural":[79],"of":[81,101,151],"targets.":[83],"Second,":[84],"Hierarchical":[86,107],"Attention":[87],"Fusion":[88],"Block":[89],"designed":[91],"guide":[93],"cross-scale":[94],"interaction":[96],"reduce":[98],"propagation":[100],"background-dominated":[102],"information.":[103],"Third,":[104],"Distribution-aware":[106],"Self-Attention":[108],"encoder":[109],"incorporated":[111],"model":[113,142,181],"response":[115],"distributions":[116],"during":[117],"global":[118],"semantic":[119],"representation.":[120],"Experiments":[121],"HIT-UAV":[123],"SIRST":[125],"show":[126],"that":[127,172],"SASE-DETR":[128,173],"improves":[129],"mAP@0.5":[130],"by":[131],"3.7%":[132],"2.5%":[134],"compared":[135],"RT-DETR-r18,":[137],"respectively.":[138],"Meanwhile,":[139],"contains":[143],"16.7M":[144],"parameters":[145],"achieves":[147],"inference":[149,185],"speed":[150],"approximately":[152],"84":[153],"FPS.":[154],"Additional":[155],"evaluation":[156],"IRSTD-1K":[158],"further":[159],"demonstrates":[160],"its":[161],"stable":[162],"generalization":[163],"different":[165],"data":[167],"distributions.":[168],"These":[169],"results":[170],"indicate":[171],"provides":[174],"favorable":[176],"trade-off":[177],"between":[178],"accuracy,":[180],"complexity,":[182],"real-time":[184],"for":[186],"detection.":[190]},"counts_by_year":[],"updated_date":"2026-07-20T05:51:44.042241","created_date":"2026-07-19T00:00:00"}