{"id":"https://openalex.org/W4407601591","doi":"https://doi.org/10.1145/3709026.3709109","title":"Cosine Similarity Guided Joint Modeling of Foreground and Background for Incremental Object Detection in Drone Images","display_name":"Cosine Similarity Guided Joint Modeling of Foreground and Background for Incremental Object Detection in Drone Images","publication_year":2024,"publication_date":"2024-12-06","ids":{"openalex":"https://openalex.org/W4407601591","doi":"https://doi.org/10.1145/3709026.3709109"},"language":"en","primary_location":{"id":"doi:10.1145/3709026.3709109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709026.3709109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3709026.3709109","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117779791","display_name":"Wei Li","orcid":"https://orcid.org/0009-0008-5750-9250"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Li","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120313172","display_name":"Zhenyu Wang","orcid":"https://orcid.org/0009-0001-9415-1859"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019612977","display_name":"Simin Li","orcid":"https://orcid.org/0000-0001-6355-2978"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simin Li","raw_affiliation_strings":["Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030965866","display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5117779791"],"corresponding_institution_ids":["https://openalex.org/I4210156423","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28445978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"38"},"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":0.998199999332428,"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":0.998199999332428,"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":0.9977999925613403,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9941999912261963,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7048583626747131},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.6970356702804565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689444899559021},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6880174279212952},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6178587675094604},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6103736162185669},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5783877372741699},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5275207161903381},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4705629348754883},{"id":"https://openalex.org/keywords/foreground-detection","display_name":"Foreground detection","score":0.46349143981933594},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4181603789329529},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4016949236392975},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2095390260219574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09629559516906738}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7048583626747131},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6970356702804565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689444899559021},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6880174279212952},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6178587675094604},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6103736162185669},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5783877372741699},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5275207161903381},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4705629348754883},{"id":"https://openalex.org/C2779769447","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Foreground detection","level":4,"score":0.46349143981933594},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4181603789329529},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016949236392975},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2095390260219574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09629559516906738},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3709026.3709109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709026.3709109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3709026.3709109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709026.3709109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2962966271","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964189064","https://openalex.org/W2964241181","https://openalex.org/W2984276908","https://openalex.org/W2989611864","https://openalex.org/W3106250896","https://openalex.org/W3168149265","https://openalex.org/W3180392831","https://openalex.org/W4207080468","https://openalex.org/W4225484930","https://openalex.org/W4226029051","https://openalex.org/W4292794069","https://openalex.org/W4313028293","https://openalex.org/W4386076053","https://openalex.org/W4386076281","https://openalex.org/W4390873638"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2123129869","https://openalex.org/W2360918960","https://openalex.org/W1987287817"],"abstract_inverted_index":{"Incremental":[0],"object":[1,30,68,79,91],"detection":[2,31,69,80,92],"(IOD)":[3],"aims":[4],"to":[5,28,105,138],"learn":[6],"the":[7,38,60,95,101,127,144,167,172,179,183,187,201,219,242,252],"localization":[8],"and":[9,100,116,166,249,254],"classification":[10,157,204],"of":[11,41,129,156,163,175,203,211,224],"new":[12],"classes":[13,99,149,165],"from":[14],"continuously":[15],"arriving":[16],"data,":[17],"while":[18],"maintaining":[19],"performance":[20,65],"on":[21,34,122,126,218],"previously":[22],"learned":[23],"old":[24,98,148,164,184],"classes.":[25],"Existing":[26],"research":[27],"incremental":[29,67,78,90,151,239],"primarily":[32],"focuses":[33],"natural":[35],"scenes;":[36],"however,":[37],"dynamic":[39],"characteristics":[40],"aerial":[42,83,225],"scenarios":[43,48],"present":[44],"unique":[45],"challenges.":[46],"These":[47],"often":[49],"involve":[50],"small,":[51],"numerous":[52],"objects":[53],"that":[54,88],"can":[55],"easily":[56],"be":[57],"confused":[58],"with":[59,186,241],"background,":[61],"resulting":[62],"in":[63,70,82,150,251],"inadequate":[64],"for":[66,147,200,208],"drone":[71,106],"applications.":[72],"In":[73],"our":[74],"study,":[75],"we":[76,112,134,159],"investigate":[77],"specifically":[81],"scenarios.":[84],"We":[85,214],"have":[86],"identified":[87],"existing":[89],"methods":[93,236],"exacerbate":[94],"confusion":[96],"between":[97],"background":[102,117,168,180,212],"when":[103],"applied":[104],"environments.":[107],"To":[108,170],"address":[109],"this":[110],"issue,":[111],"propose":[113],"a":[114],"foreground":[115],"joint":[118,161],"modeling":[119,162],"approach":[120],"based":[121],"cosine":[123],"similarity.":[124],"First,":[125],"basis":[128],"standard":[130],"knowledge":[131],"distillation":[132],"method,":[133],"utilize":[135],"old-class":[136,140],"model":[137],"extract":[139],"foreground,":[141],"which":[142,222],"supplements":[143],"missing":[145],"annotations":[146],"steps.":[152],"Second,":[153],"during":[154],"calculation":[155,202],"loss,":[158,205],"incorporate":[160],"class.":[169,213],"obtain":[171],"probability":[173,181,195],"prediction":[174],"negative":[176],"samples,":[177],"besides":[178],"output,":[182],"categories":[185],"highest":[188],"normalized":[189],"logits":[190],"are":[191,197],"also":[192],"considered.":[193],"Their":[194],"predictions":[196],"added":[198],"together":[199],"utimately":[206],"utilized":[207],"gradient":[209],"backpropagation":[210],"conduct":[215],"extensive":[216],"experiments":[217],"VisDrone":[220],"dataset,":[221],"consists":[223],"images.":[226],"Our":[227],"method":[228],"demonstrates":[229],"significant":[230],"improvements":[231],"over":[232],"current":[233],"state-of-the-art":[234],"baseline":[235],"under":[237],"various":[238],"settings,":[240,256],"Average":[243],"Precision":[244],"(AP)":[245],"improvement":[246],"by":[247],"0.64%":[248],"0.73%":[250],"two-step":[253],"multi-step":[255],"respectively.":[257]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}