{"id":"https://openalex.org/W4384499126","doi":"https://doi.org/10.1109/tse.2023.3295801","title":"Code2Img: Tree-Based Image Transformation for Scalable Code Clone Detection","display_name":"Code2Img: Tree-Based Image Transformation for Scalable Code Clone Detection","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384499126","doi":"https://doi.org/10.1109/tse.2023.3295801"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2023.3295801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3295801","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5043631596","display_name":"Yutao Hu","orcid":"https://orcid.org/0000-0001-6388-8455"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Hu","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6388-8455","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103074582","display_name":"Yilin Fang","orcid":"https://orcid.org/0009-0004-7095-7366"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Fang","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-7095-7366","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101592342","display_name":"Yifan Sun","orcid":"https://orcid.org/0009-0006-4277-3353"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0006-4277-3353","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072354439","display_name":"Yaru Jia","orcid":"https://orcid.org/0009-0000-4935-9127"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaru Jia","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-4935-9127","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056381213","display_name":"Yueming Wu","orcid":"https://orcid.org/0000-0002-1515-3558"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yueming Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1515-3558","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074676946","display_name":"Deqing Zou","orcid":"https://orcid.org/0000-0001-8534-5048"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqing Zou","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8534-5048","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9349,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.94191785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"49","issue":"9","first_page":"4429","last_page":"4442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7871689796447754},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6035578846931458},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5819971561431885},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5748045444488525},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.5114613771438599},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5039293169975281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4774787425994873},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45105093717575073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3479970097541809},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32546716928482056},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.26970958709716797},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11911344528198242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11170706152915955},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07956591248512268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871689796447754},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6035578846931458},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5819971561431885},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5748045444488525},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.5114613771438599},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5039293169975281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4774787425994873},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45105093717575073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3479970097541809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32546716928482056},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.26970958709716797},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11911344528198242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11170706152915955},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07956591248512268},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2023.3295801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3295801","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5762890969","display_name":null,"funder_award_id":"62172168","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W154143472","https://openalex.org/W2056830820","https://openalex.org/W2065622239","https://openalex.org/W2109759383","https://openalex.org/W2120326119","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2131477050","https://openalex.org/W2138756793","https://openalex.org/W2148099973","https://openalex.org/W2149864547","https://openalex.org/W2158439356","https://openalex.org/W2161061943","https://openalex.org/W2165739648","https://openalex.org/W2282866165","https://openalex.org/W2298313545","https://openalex.org/W2511803001","https://openalex.org/W2587019100","https://openalex.org/W2598761292","https://openalex.org/W2621103691","https://openalex.org/W2728599219","https://openalex.org/W2741705590","https://openalex.org/W2762844179","https://openalex.org/W2767717989","https://openalex.org/W2768306496","https://openalex.org/W2794744252","https://openalex.org/W2807866521","https://openalex.org/W2809192110","https://openalex.org/W2890730120","https://openalex.org/W2899171197","https://openalex.org/W2919074952","https://openalex.org/W2955426500","https://openalex.org/W3004750786","https://openalex.org/W3014307249","https://openalex.org/W3014339000","https://openalex.org/W3045279034","https://openalex.org/W3105535951","https://openalex.org/W3125205154","https://openalex.org/W3189457934","https://openalex.org/W3193289990","https://openalex.org/W4234407387","https://openalex.org/W4301168982","https://openalex.org/W4312838748","https://openalex.org/W4313563607","https://openalex.org/W6683923952","https://openalex.org/W6697318023","https://openalex.org/W6733081445"],"related_works":["https://openalex.org/W4389751695","https://openalex.org/W4310447811","https://openalex.org/W2165004968","https://openalex.org/W2320787857","https://openalex.org/W3086207785","https://openalex.org/W2969229669","https://openalex.org/W3012064729","https://openalex.org/W2955426500","https://openalex.org/W2388254906","https://openalex.org/W3049398420"],"abstract_inverted_index":{"Code":[0],"clone":[1,17,23,56,79,101,118,234,267],"detection":[2,20,81,255],"is":[3],"an":[4,153],"active":[5],"research":[6],"domain":[7],"of":[8,62,64,73,88,143,165,207,219,253],"software":[9],"engineering.":[10],"There":[11],"are":[12,51,83],"two":[13],"core":[14],"demands":[15],"for":[16],"detection:":[18],"scalable":[19,26,265],"and":[21,40,48,162,184,228,257],"complicated":[22,55,108,266],"detection.":[24,268],"For":[25,129],"detection,":[27],"existing":[28],"approaches":[29,50],"treat":[30],"the":[31,46,60,86,112,121,126,135,140,144,158,166,171,176,191,204,208,216,243,248],"source":[32,113],"code":[33,65,74,100],"as":[34],"a":[35,98,180,199],"text":[36],"or":[37],"token":[38],"sequence":[39],"then":[41],"calculate":[42],"their":[43],"similarity.":[44],"However,":[45],"text-based":[47],"token-based":[49],"difficult":[52],"to":[53,59,90,124,156,174,264],"detect":[54,212],"types":[57,80],"due":[58],"lack":[61],"consideration":[63],"structure.":[66],"The":[67,238],"methods":[68],"based":[69,138],"on":[70,139,226],"intermediate":[71],"representations":[72,89],"can":[75,195],"effectively":[76],"achieve":[77],"complex":[78,193],"but":[82],"limited":[84],"by":[85,120,214],"complexity":[87],"be":[91,196,262],"scalable.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,115,133,151,169,211],"proposeCode2Img,":[97],"tree-based":[99],"detector,":[102],"which":[103],"satisfies":[104],"scalability":[105,229],"while":[106,202],"detecting":[107],"clones":[109,213],"effectively.":[110],"Given":[111],"code,":[114],"first":[116],"perform":[117],"filtering":[119],"inverted":[122],"index":[123],"locate":[125],"suspected":[127,131],"clones.":[128],"each":[130],"clone,":[132],"create":[134],"adjacency":[136,141,177],"image":[137,154,178,183],"matrix":[142],"normalized":[145],"abstract":[146],"syntax":[147],"tree":[148,194],"(AST).":[149],"Then":[150],"design":[152],"encoder":[155],"highlight":[157],"structural":[159,205],"details":[160],"further":[161],"refine":[163],"pixels":[164],"image.":[167],"Specifically,":[168],"employ":[170],"Markov":[172],"model":[173],"encode":[175],"into":[179,198],"state":[181],"probability":[182],"remove":[185],"its":[186],"useless":[187],"pixels.":[188],"By":[189],"this,":[190],"original":[192],"transformed":[197],"one-dimensional":[200],"vector":[201],"preserving":[203],"feature":[206],"AST.":[209],"Finally,":[210],"calculating":[215],"Jaccard":[217],"Similarity":[218],"these":[220],"vectors.":[221],"We":[222],"conduct":[223],"comparative":[224,249],"evaluations":[225],"effectiveness":[227,256],"with":[230],"eight":[231],"other":[232],"state-of-the-art":[233],"detectors":[235],"(SourcererCC,NIL,LVMapper,Nicad,Siamese,CCAligner,Deckard,":[236],"andYang2018).":[237],"experimental":[239],"results":[240],"show":[241],"thatCode2Imgachieves":[242],"best":[244],"performance":[245],"among":[246],"all":[247],"tools":[250],"in":[251],"terms":[252],"both":[254],"scalability.":[258],"It":[259],"indicates":[260],"thatCode2Imgcan":[261],"applicable":[263]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}