{"id":"https://openalex.org/W4388425992","doi":"https://doi.org/10.1109/dsaa60987.2023.10302637","title":"A CNN-Transformer Hybrid Network for Multi-scale object detection","display_name":"A CNN-Transformer Hybrid Network for Multi-scale object detection","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4388425992","doi":"https://doi.org/10.1109/dsaa60987.2023.10302637"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa60987.2023.10302637","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsaa60987.2023.10302637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","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":"Jianhong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianhong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694240","display_name":"Yingdong Ma","orcid":"https://orcid.org/0000-0001-5446-8635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingdong Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52692543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9944999814033508,"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":0.7035605907440186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6403604745864868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719954371452332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5116210579872131},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4424087703227997},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4410872757434845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3441534638404846},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.19813251495361328},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11717566847801208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035605907440186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6403604745864868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719954371452332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5116210579872131},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4424087703227997},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4410872757434845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3441534638404846},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.19813251495361328},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11717566847801208},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa60987.2023.10302637","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsaa60987.2023.10302637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","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":56,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2884561390","https://openalex.org/W2970575838","https://openalex.org/W2982770724","https://openalex.org/W2988452521","https://openalex.org/W3018757597","https://openalex.org/W3028147364","https://openalex.org/W3034307881","https://openalex.org/W3034552520","https://openalex.org/W3034971973","https://openalex.org/W3035396860","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3100070763","https://openalex.org/W3106250896","https://openalex.org/W3106728613","https://openalex.org/W3107331169","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3159663321","https://openalex.org/W3159778524","https://openalex.org/W3160694286","https://openalex.org/W3183430956","https://openalex.org/W3203003533","https://openalex.org/W3206263120","https://openalex.org/W4214493665","https://openalex.org/W4225745741","https://openalex.org/W4226224676","https://openalex.org/W4285483923","https://openalex.org/W4293584584","https://openalex.org/W4312412889","https://openalex.org/W4312950730","https://openalex.org/W4313119505","https://openalex.org/W4391021637","https://openalex.org/W6639102338","https://openalex.org/W6735463952","https://openalex.org/W6750227808","https://openalex.org/W6760947256","https://openalex.org/W6767109091","https://openalex.org/W6777046832","https://openalex.org/W6777822163","https://openalex.org/W6778485988","https://openalex.org/W6784333009","https://openalex.org/W6785652829","https://openalex.org/W6795062860","https://openalex.org/W6795308139","https://openalex.org/W6804904660","https://openalex.org/W6840156360"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2082269393","https://openalex.org/W2043960970"],"abstract_inverted_index":{"Recently,":[0],"Transformer-based":[1],"methods":[2],"have":[3],"been":[4],"the":[5,25,59,78,82,93,141,151],"main":[6],"framework":[7],"in":[8,51],"various":[9],"computer":[10],"vision":[11],"tasks.":[12],"Vision":[13],"transformers":[14],"achieve":[15],"object":[16,155],"detection":[17],"based":[18,120],"on":[19,140],"sequence":[20],"of":[21,27,81,98,153],"visual":[22,94],"tokens,":[23],"lacking":[24],"ability":[26],"extracting":[28],"local":[29,63],"context":[30],"and":[31,58,68,85,116,135],"dealing":[32],"with":[33,46,88],"scale":[34],"variance.":[35],"To":[36],"tackle":[37],"this":[38],"problem,":[39],"we":[40,76,105],"propose":[41],"a":[42,107],"hybrid":[43],"CNN-transformer":[44],"model":[45],"multiple":[47],"dual-branch":[48],"transformer":[49,53,69,86,102],"blocks":[50],"which":[52],"branch":[54,61,67,70,84,87],"captures":[55],"global":[56],"dependences":[57],"CNN":[60,83],"enhances":[62],"context.":[64],"As":[65],"convolution":[66],"pay":[71],"attention":[72],"to":[73,111],"different-level":[74],"information,":[75],"combine":[77],"output":[79],"features":[80,115],"adaptive":[89],"weights":[90],"calculated":[91],"from":[92,101],"content.":[95],"Moreover,":[96],"instead":[97],"detecting":[99],"objects":[100],"outputs":[103],"directly,":[104],"introduce":[106],"feature":[108,118,127],"aggregation":[109,128],"module":[110,129],"fuse":[112],"different":[113],"levels":[114],"construct":[117],"pyramid":[119],"upon":[121],"these":[122],"multi-level":[123],"features.":[124,137],"The":[125],"proposed":[126],"alleviates":[130],"semantic":[131],"gap":[132],"between":[133],"high-level":[134],"low-level":[136],"Experimental":[138],"results":[139],"MS":[142],"COCO":[143],"dataset":[144],"show":[145],"that":[146],"our":[147],"method":[148],"significantly":[149],"improves":[150],"performance":[152],"multi-scale":[154],"detection.":[156]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}