{"id":"https://openalex.org/W4415708491","doi":"https://doi.org/10.1109/icme59968.2025.11210059","title":"SODMAMBA-DETR:A Small Object DETR Detector Based on a Mamba Encoder","display_name":"SODMAMBA-DETR:A Small Object DETR Detector Based on a Mamba Encoder","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708491","doi":"https://doi.org/10.1109/icme59968.2025.11210059"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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":"Yiheng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiheng Sun","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162896","display_name":"Xiaopeng Hu","orcid":"https://orcid.org/0000-0001-7817-4703"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Hu","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011857394","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0001-5788-0334"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063794550","display_name":"Xinrong Wu","orcid":"https://orcid.org/0000-0001-5306-4137"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrong Wu","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784318","display_name":"Ying Zhou","orcid":"https://orcid.org/0000-0003-4953-4161"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhou","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083390005","display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0002-3924-5537"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101700202","display_name":"Rongqi Zhu","orcid":"https://orcid.org/0000-0002-6376-8258"},"institutions":[{"id":"https://openalex.org/I153374732","display_name":"Liaoning Normal University","ror":"https://ror.org/04c3cgg32","country_code":"CN","type":"education","lineage":["https://openalex.org/I153374732"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongqi Zhu","raw_affiliation_strings":["The High School Affiliated to Liaoning Normal University"],"affiliations":[{"raw_affiliation_string":"The High School Affiliated to Liaoning Normal University","institution_ids":["https://openalex.org/I153374732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30585841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.960099995136261,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.960099995136261,"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":0.0052999998442828655,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.003599999938160181,"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/encoder","display_name":"Encoder","score":0.8029999732971191},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5641000270843506},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48489999771118164}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8029999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455999851226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5145000219345093},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3763999938964844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2987322772","https://openalex.org/W3034552520","https://openalex.org/W3096609285","https://openalex.org/W4312312588","https://openalex.org/W4312823573","https://openalex.org/W4385654692","https://openalex.org/W4385737867","https://openalex.org/W4386065740","https://openalex.org/W4386076053","https://openalex.org/W4402351415","https://openalex.org/W4402754006","https://openalex.org/W4403606929","https://openalex.org/W4409367296"],"related_works":[],"abstract_inverted_index":{"Small":[0],"objects,":[1],"due":[2,44],"to":[3,11,15,31,45,80],"their":[4],"limited":[5],"pixel":[6],"size,":[7],"are":[8],"highly":[9],"susceptible":[10],"background":[12],"noise,":[13],"leading":[14],"the":[16],"loss":[17],"of":[18],"critical":[19,84],"details":[20,102],"during":[21],"feature":[22],"extraction.":[23],"Some":[24],"existing":[25,122],"Transformer-based":[26],"detectors":[27],"rely":[28],"on":[29,83,111],"encoders":[30,51],"capture":[32],"global":[33],"contextual":[34],"information":[35],"for":[36],"small":[37],"object":[38],"detection":[39,60],"in":[40,128],"complex":[41,129],"environments.":[42],"However,":[43],"interference":[46],"from":[47],"intricate":[48],"backgrounds,":[49],"attention-based":[50],"often":[52],"learn":[53],"redundant":[54],"or":[55],"irrelevant":[56],"features,":[57],"which":[58,69],"degrade":[59],"performance.":[61],"To":[62],"overcome":[63],"this":[64],"challenge,":[65],"we":[66],"introduce":[67],"SODMAMBA-DETR,":[68],"incorporates":[70],"a":[71,76,88,94],"SODMAMBA":[72],"encoder":[73],"equipped":[74],"with":[75],"selective":[77],"learning":[78],"mechanism":[79],"effectively":[81],"focus":[82],"information.":[85],"By":[86],"integrating":[87],"Multi-scale":[89],"Feature":[90],"Fusion":[91],"Neck":[92],"and":[93,103,113,124],"MFFAW":[95],"module,":[96],"our":[97,118],"framework":[98,119],"efficiently":[99],"captures":[100],"local":[101],"fuses":[104],"features":[105],"across":[106],"multiple":[107],"scales.":[108],"Experimental":[109],"results":[110],"VisDrone":[112],"AI-TOD":[114],"datasets":[115],"demonstrate":[116],"that":[117],"significantly":[120],"outperforms":[121],"Transformer":[123],"CNN-based":[125],"detectors,":[126],"particularly":[127],"scenarios.":[130]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-30T00:00:00"}