{"id":"https://openalex.org/W4409787718","doi":"https://doi.org/10.1142/s0218001425560014","title":"Few-Shot Counting with Multi-Scale Vision Transformers and Attention Mechanisms","display_name":"Few-Shot Counting with Multi-Scale Vision Transformers and Attention Mechanisms","publication_year":2025,"publication_date":"2025-04-26","ids":{"openalex":"https://openalex.org/W4409787718","doi":"https://doi.org/10.1142/s0218001425560014"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425560014","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425560014","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5103096202","display_name":"Xiaopan Chen","orcid":"https://orcid.org/0000-0002-2766-9367"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopan Chen","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-2766-9367","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwei Dong","orcid":"https://orcid.org/0009-0004-7349-7596"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Dong","raw_affiliation_strings":["Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, P. R. China"],"raw_orcid":"https://orcid.org/0009-0004-7349-7596","affiliations":[{"raw_affiliation_string":"Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, P. R. China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012689262","display_name":"Xiaoke Zhu","orcid":"https://orcid.org/0000-0002-0664-1832"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Zhu","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0664-1832","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403556","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0003-2176-3835"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-2176-3835","affiliations":[{"raw_affiliation_string":"Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, P. R. China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119013736","display_name":"Caihong Yuan","orcid":"https://orcid.org/0009-0004-9622-4179"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caihong Yuan","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China"],"raw_orcid":"https://orcid.org/0009-0004-9622-4179","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, P. R. China","institution_ids":["https://openalex.org/I173899330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173899330"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69276252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"08","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9932000041007996,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9932000041007996,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6761593818664551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6363985538482666},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5477619767189026},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5398643612861633},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5312806367874146},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4898621737957001},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36964502930641174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11486124992370605},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07778286933898926}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6761593818664551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363985538482666},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5477619767189026},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5398643612861633},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5312806367874146},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4898621737957001},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36964502930641174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11486124992370605},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07778286933898926},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425560014","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425560014","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2080481652","https://openalex.org/W2347064614","https://openalex.org/W2519281173","https://openalex.org/W2899128648","https://openalex.org/W2949333977","https://openalex.org/W2962921175","https://openalex.org/W2963499661","https://openalex.org/W2964290048","https://openalex.org/W2971900262","https://openalex.org/W3002638829","https://openalex.org/W3027606690","https://openalex.org/W3170764266","https://openalex.org/W3212886205","https://openalex.org/W4221148940","https://openalex.org/W4221160666","https://openalex.org/W4312392894","https://openalex.org/W4312791242","https://openalex.org/W4390591015","https://openalex.org/W4390836729","https://openalex.org/W4390874575","https://openalex.org/W4393153748","https://openalex.org/W4405270571"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Object":[0],"counting":[1,38,47,241],"is":[2,265],"a":[3,42,92,101,125,173,194,202,245],"fundamental":[4],"task":[5],"in":[6,12,53,106],"computer":[7],"vision,":[8],"with":[9,48,172],"critical":[10],"applications":[11],"areas":[13],"such":[14,65],"as":[15,41,66],"crowd":[16],"monitoring":[17],"and":[18,32,72,201,224],"ecological":[19],"conservation.":[20],"Traditional":[21],"methods":[22,78],"typically":[23],"rely":[24],"on":[25,177,183],"large-scale":[26],"annotated":[27,50],"datasets,":[28],"which":[29,108],"are":[30],"costly":[31],"time-consuming":[33],"to":[34,63,81,116,130,135,154,167,211,253],"obtain.":[35],"Few-shot":[36],"object":[37,240],"has":[39],"emerged":[40],"promising":[43],"solution,":[44],"enabling":[45],"accurate":[46],"minimal":[49],"samples.":[51],"However,":[52],"real-world":[54],"scenarios,":[55],"objects":[56,118],"often":[57],"exhibit":[58],"significant":[59],"scale":[60],"variations":[61],"due":[62],"factors":[64],"view":[67],"distortion,":[68],"varying":[69,120],"shooting":[70],"distances,":[71],"inherent":[73],"size":[74],"differences.":[75],"Existing":[76],"few-shot":[77,239,251],"usually":[79],"struggle":[80],"address":[82,87],"this":[83],"challenge":[84],"effectively.":[85],"To":[86],"these":[88],"issues,":[89],"we":[90,99,123,147],"propose":[91],"Scale-Aware":[93],"Vision":[94],"Transformer":[95],"(SAViT)":[96],"framework.":[97],"Specifically,":[98],"design":[100],"multi-scale":[102,258],"dilated":[103],"convolution":[104,112],"module":[105],"SAViT,":[107],"can":[109],"adaptively":[110],"adjust":[111],"kernel":[113],"sampling":[114],"rates":[115],"handle":[117],"of":[119,190,199,208,262],"sizes.":[121],"Additionally,":[122],"incorporate":[124],"global":[126],"channel":[127],"attention":[128],"mechanism":[129],"strengthen":[131],"the":[132,149,162,178,184,188,212],"model\u2019s":[133],"ability":[134],"capture":[136],"robust":[137],"feature":[138],"representations,":[139],"thereby":[140],"improving":[141],"detection":[142],"accuracy.":[143],"For":[144],"practical":[145,247],"usability,":[146],"integrate":[148],"Segment":[150],"Anything":[151],"Model":[152],"(SAM)":[153],"create":[155],"an":[156,235],"exemplar":[157,170],"box":[158],"selection":[159],"module,":[160],"simplifying":[161],"process":[163],"by":[164,220,226],"allowing":[165],"users":[166],"generate":[168],"precise":[169],"boxes":[171],"single":[174],"line":[175],"drawn":[176],"target":[179],"object.":[180],"Extensive":[181],"experiments":[182],"FSC-147":[185],"dataset":[186],"demonstrate":[187],"effectiveness":[189],"our":[191,216,263],"approach,":[192],"achieving":[193],"Mean":[195,204],"Absolute":[196],"Error":[197,206],"(MAE)":[198],"8.92":[200],"Root":[203],"Squared":[205],"(RMSE)":[207],"31.26.":[209],"Compared":[210],"state-of-the-art":[213],"method,":[214],"CACViT,":[215],"model":[217],"reduces":[218],"MAE":[219],"0.21":[221],"(2.30%":[222],"improvement)":[223],"RMSE":[225],"17.7":[227],"(36.15%":[228],"improvement).":[229],"Our":[230],"approach":[231],"not":[232],"only":[233],"provides":[234,244],"effective":[236],"solution":[237],"for":[238,249],"but":[242],"also":[243],"new":[246],"paradigm":[248],"extending":[250],"learning":[252],"complex":[254],"vision":[255],"tasks":[256],"requiring":[257],"reasoning.":[259],"The":[260],"code":[261],"paper":[264],"available":[266],"at":[267],"https://github.com/BlouseDong/SAViT":[268],".":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}