{"id":"https://openalex.org/W4391306407","doi":"https://doi.org/10.1109/smc53992.2023.10393952","title":"Object Detection via Multi-Scale Token Based on Vision Transformer","display_name":"Object Detection via Multi-Scale Token Based on Vision Transformer","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391306407","doi":"https://doi.org/10.1109/smc53992.2023.10393952"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10393952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10393952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067434249","display_name":"Xiao Yu","orcid":"https://orcid.org/0000-0001-5762-2503"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xiao","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045753906","display_name":"Tao Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qiu","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074958556","display_name":"Xinqi Jiang","orcid":"https://orcid.org/0009-0002-7503-0231"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinqi Jiang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703892","display_name":"Qi Yang","orcid":"https://orcid.org/0000-0001-6969-8724"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052276737","display_name":"Zhaowei Shang","orcid":"https://orcid.org/0000-0002-1588-1387"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaowei Shang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664915","display_name":"Taiping Zhang","orcid":"https://orcid.org/0000-0001-9891-4203"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiping Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9520000219345093,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9520000219345093,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9186000227928162,"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":0.9121000170707703,"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/computer-science","display_name":"Computer science","score":0.704031765460968},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6573723554611206},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6544815897941589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6255808472633362},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5051324963569641},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46380260586738586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3171095848083496},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12477463483810425},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12132954597473145},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08801954984664917},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.061427414417266846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704031765460968},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6573723554611206},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6544815897941589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6255808472633362},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5051324963569641},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46380260586738586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3171095848083496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12477463483810425},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12132954597473145},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08801954984664917},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.061427414417266846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10393952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10393952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2031489346","https://openalex.org/W2179352600","https://openalex.org/W2565639579","https://openalex.org/W2773495332","https://openalex.org/W2955425717","https://openalex.org/W2963351448","https://openalex.org/W2963563276","https://openalex.org/W2964350391","https://openalex.org/W3018757597","https://openalex.org/W3096609285","https://openalex.org/W3098722327","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3171087525","https://openalex.org/W3183430956","https://openalex.org/W3203692465","https://openalex.org/W3211490618","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4385245566","https://openalex.org/W4389666313","https://openalex.org/W6739901393","https://openalex.org/W6762718338","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4385009901","https://openalex.org/W4285141722","https://openalex.org/W3016124757"],"abstract_inverted_index":{"Visual":[0],"transformers":[1,10],"have":[2],"achieved":[3],"impressive":[4],"performance":[5,101,140,179],"on":[6,13,74,119,167,180],"object":[7,46,181],"detection.":[8,182],"Traditional":[9],"only":[11],"focus":[12,118],"multi-scale":[14],"features":[15,30,93,131],"between":[16],"tokens":[17],"and":[18,82,102,132,152],"tokens.":[19],"However,":[20],"these":[21],"methods":[22],"do":[23],"not":[24],"pay":[25],"attention":[26],"to":[27,38,88,117,128],"the":[28,39,45,59,75,84,95,100,106,123,126,138,150,157],"fine-grained":[29],"inside":[31],"a":[32,55,114,177],"single":[33],"token,":[34],"which":[35,62],"can":[36,175],"lead":[37],"loss":[40],"of":[41,64,79,105],"semantic":[42],"information":[43,121,154,161],"in":[44,122],"detection":[47],"task.":[48],"To":[49],"address":[50],"this":[51],"issue,":[52],"we":[53],"propose":[54],"novel":[56],"network":[57,116,158],"for":[58],"above":[60],"problem,":[61],"consists":[63],"three":[65],"components,":[66],"(1)":[67],"Internal":[68],"Multiscale":[69],"Token":[70],"Module":[71,111,147],"(IMTM)":[72],"focuses":[73],"receptive":[76],"field":[77],"size":[78,87],"each":[80],"token":[81,85],"transforms":[83],"dimension":[86],"effectively":[89],"extract":[90],"more":[91],"multiscale":[92],"within":[94],"self-attention":[96],"layer,":[97],"thereby":[98],"improving":[99,137],"generalization":[103],"ability":[104],"model.":[107],"(2)":[108],"Differential":[109],"Filter":[110],"(DFM)":[112],"uses":[113],"convolutional":[115],"high-frequency":[120],"image,":[124],"helping":[125],"Transformer":[127],"learn":[129],"edge":[130],"establish":[133],"local":[134,151],"context,":[135],"while":[136],"model":[139],"through":[141],"residual":[142],"connections.":[143],"(3)":[144],"Feature":[145],"Fusion":[146],"(FFM)":[148],"enhances":[149],"global":[153],"extracted":[155],"by":[156,159],"fusing":[160],"from":[162],"different":[163],"dimensions.":[164],"Extensive":[165],"experiments":[166],"PASCAL":[168],"VOC":[169],"shows":[170],"that":[171],"our":[172],"proposed":[173],"method":[174],"achieve":[176],"state-of-the-art":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
