{"id":"https://openalex.org/W7125925830","doi":"https://doi.org/10.1109/smc58881.2025.11342926","title":"LLM-DETR: An Enhanced DETR with a Large Language Model-Inspired Attention Mechanism for Object Detection","display_name":"LLM-DETR: An Enhanced DETR with a Large Language Model-Inspired Attention Mechanism for Object Detection","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125925830","doi":"https://doi.org/10.1109/smc58881.2025.11342926"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342926","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 Systems, Man, and Cybernetics (SMC)","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":"https://openalex.org/A5036481579","display_name":"Kuan-Hsien Liu","orcid":"https://orcid.org/0000-0002-1411-2113"},"institutions":[{"id":"https://openalex.org/I131948415","display_name":"National Taichung University of Science and Technology","ror":"https://ror.org/05bgcav40","country_code":"TW","type":"education","lineage":["https://openalex.org/I131948415"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kuan-Hsien Liu","raw_affiliation_strings":["National Taichung University of Science and Technology,Department of Computer Science and Information Engineering,Taichung,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taichung University of Science and Technology,Department of Computer Science and Information Engineering,Taichung,Taiwan","institution_ids":["https://openalex.org/I131948415"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085396421","display_name":"Mingru Wang","orcid":"https://orcid.org/0009-0009-8007-3261"},"institutions":[{"id":"https://openalex.org/I131948415","display_name":"National Taichung University of Science and Technology","ror":"https://ror.org/05bgcav40","country_code":"TW","type":"education","lineage":["https://openalex.org/I131948415"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mingru Wang","raw_affiliation_strings":["National Taichung University of Science and Technology,Department of Computer Science and Information Engineering,Taichung,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taichung University of Science and Technology,Department of Computer Science and Information Engineering,Taichung,Taiwan","institution_ids":["https://openalex.org/I131948415"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124059639","display_name":"Tsung-Jung Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Jung Liu","raw_affiliation_strings":["National Chung Hsing University,Department of Electrical Engineering,Taichung,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chung Hsing University,Department of Electrical Engineering,Taichung,Taiwan","institution_ids":["https://openalex.org/I162838928"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036481579"],"corresponding_institution_ids":["https://openalex.org/I131948415"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68600766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6071000099182129,"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":0.6071000099182129,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20280000567436218,"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":0.047200001776218414,"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/object","display_name":"Object (grammar)","score":0.6707000136375427},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6140000224113464},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4964999854564667},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.2978000044822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735000252723694},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6707000136375427},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6140000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553600013256073},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5364999771118164},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C154526789","wikidata":"https://www.wikidata.org/wiki/Q157965","display_name":"Object code","level":4,"score":0.289000004529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.27970001101493835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342926","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1567822572","https://openalex.org/W1861492603","https://openalex.org/W2114768185","https://openalex.org/W2150864004","https://openalex.org/W2194775991","https://openalex.org/W2410358280","https://openalex.org/W2943229868","https://openalex.org/W2943488693","https://openalex.org/W2946726474","https://openalex.org/W2963091558","https://openalex.org/W3096609285","https://openalex.org/W3112068703","https://openalex.org/W3112978863","https://openalex.org/W3116501232","https://openalex.org/W3127708505","https://openalex.org/W3138516171","https://openalex.org/W3159178846","https://openalex.org/W3159481202","https://openalex.org/W3203020760","https://openalex.org/W4292829834","https://openalex.org/W4312312588","https://openalex.org/W4385245566","https://openalex.org/W4386066469","https://openalex.org/W4386074309","https://openalex.org/W4388979610","https://openalex.org/W4389518760","https://openalex.org/W4413277948"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"LLM-DETR,":[2],"an":[3],"enhanced":[4],"version":[5],"of":[6,56],"the":[7,28,43,54],"DETR":[8],"(DEtection":[9],"TRansformer)":[10],"framework":[11],"that":[12],"integrates":[13],"advanced":[14],"attention":[15,58],"mechanisms":[16,59],"inspired":[17],"by":[18],"large":[19],"language":[20],"models":[21],"(LLMs)":[22],"for":[23,60,70],"object":[24,62],"detection.":[25],"Applied":[26],"to":[27],"MS":[29],"COCO":[30],"2017":[31],"dataset,":[32],"LLM-DETR":[33,72],"demonstrates":[34],"a":[35],"5%":[36],"increase":[37],"in":[38,65],"average":[39],"precision":[40],"(AP)":[41],"over":[42],"original":[44],"DETR,":[45],"while":[46],"exhibiting":[47],"efficient":[48],"GPU":[49],"training.":[50],"This":[51],"improvement":[52],"underscores":[53],"potential":[55],"LLM-inspired":[57],"advancing":[61],"detection":[63],"accuracy":[64],"various":[66],"domains.":[67],"The":[68],"code":[69],"our":[71],"is":[73],"publicly":[74],"available":[75],"on":[76],"GitHub:":[77],"https://github.com/mingruWang/LLM-DETR.":[78]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}
