{"id":"https://openalex.org/W4387623951","doi":"https://doi.org/10.1109/tcsvt.2023.3322465","title":"Instance-Dictionary Learning for Open-World Object Detection in Autonomous Driving Scenarios","display_name":"Instance-Dictionary Learning for Open-World Object Detection in Autonomous Driving Scenarios","publication_year":2023,"publication_date":"2023-10-13","ids":{"openalex":"https://openalex.org/W4387623951","doi":"https://doi.org/10.1109/tcsvt.2023.3322465"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3322465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3322465","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","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/A5030001981","display_name":"Zeyu Ma","orcid":"https://orcid.org/0000-0002-2553-0679"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyu Ma","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860405","display_name":"Ziqiang Zheng","orcid":"https://orcid.org/0000-0002-1477-6040"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Zheng","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060342584","display_name":"Jiwei Wei","orcid":"https://orcid.org/0000-0003-3912-1742"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwei Wei","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China, Guangdong, China","Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China, Guangdong, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030001981"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.6524,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91956638,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"34","issue":"5","first_page":"3395","last_page":"3408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9993000030517578,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216408848762512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256645917892456},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6111628413200378},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.590205192565918},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4398545026779175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31880152225494385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216408848762512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256645917892456},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6111628413200378},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.590205192565918},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4398545026779175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31880152225494385}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3322465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3322465","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5299999713897705},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G591136627","display_name":null,"funder_award_id":"62306067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6386744776","display_name":null,"funder_award_id":"2022M720660","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W2036963181","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2589930967","https://openalex.org/W2748021867","https://openalex.org/W2789366140","https://openalex.org/W2803620531","https://openalex.org/W2896457183","https://openalex.org/W2948672349","https://openalex.org/W2955889502","https://openalex.org/W2963042258","https://openalex.org/W2963080533","https://openalex.org/W2963150697","https://openalex.org/W2963445828","https://openalex.org/W2963936013","https://openalex.org/W2964115968","https://openalex.org/W2968634921","https://openalex.org/W2982770724","https://openalex.org/W2989176720","https://openalex.org/W2997998901","https://openalex.org/W3005971801","https://openalex.org/W3014645216","https://openalex.org/W3034478348","https://openalex.org/W3034779842","https://openalex.org/W3034937575","https://openalex.org/W3035212740","https://openalex.org/W3035524453","https://openalex.org/W3035564946","https://openalex.org/W3037773948","https://openalex.org/W3088877992","https://openalex.org/W3106250896","https://openalex.org/W3108145393","https://openalex.org/W3118555031","https://openalex.org/W3121281282","https://openalex.org/W3134272453","https://openalex.org/W3160711975","https://openalex.org/W3166409449","https://openalex.org/W3173601880","https://openalex.org/W3173859428","https://openalex.org/W3176709420","https://openalex.org/W3180426564","https://openalex.org/W3185727700","https://openalex.org/W3186269967","https://openalex.org/W3201703290","https://openalex.org/W3205385460","https://openalex.org/W3206198586","https://openalex.org/W3206713300","https://openalex.org/W3207668590","https://openalex.org/W3207933943","https://openalex.org/W4200403198","https://openalex.org/W4206019878","https://openalex.org/W4226029054","https://openalex.org/W4282919414","https://openalex.org/W4282935261","https://openalex.org/W4283807782","https://openalex.org/W4287124998","https://openalex.org/W4293428377","https://openalex.org/W4300479382","https://openalex.org/W4304092541","https://openalex.org/W4312563428","https://openalex.org/W4312624173","https://openalex.org/W4312713178","https://openalex.org/W4312894362","https://openalex.org/W4313160378","https://openalex.org/W4313855701","https://openalex.org/W4364322117","https://openalex.org/W4379539360","https://openalex.org/W4386076022","https://openalex.org/W4387831758","https://openalex.org/W4390874575","https://openalex.org/W6620707391","https://openalex.org/W6755207826","https://openalex.org/W6758248578","https://openalex.org/W6762122294","https://openalex.org/W6791353385","https://openalex.org/W6810994575","https://openalex.org/W6838918575","https://openalex.org/W6845611785","https://openalex.org/W6853209222"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"an":[3],"important":[4],"and":[5,25,60,111,129,155,160,216],"valuable":[6],"open-world":[7],"object":[8,41,51,62,75,162],"detection":[9,38,52],"(OWOD)":[10],"in":[11,87,177],"autonomous":[12],"driving":[13],"scenarios,":[14],"which":[15,150],"aims":[16],"to":[17,121],"detect":[18,187],"objects":[19],"under":[20,43],"both":[21],"<italic":[22,26],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[23,27],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">domain-agnostic</i>":[24],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">category-agnostic</i>":[28],"settings":[29],"simultaneously.":[30],"Existing":[31],"OWOD":[32,113,224],"algorithms":[33],"mainly":[34],"focus":[35],"on":[36,206],"the":[37,72,124,145,152,158,172,178,188],"of":[39],"pre-defined":[40],"categories":[42,63,190,209],"various":[44],"conditions":[45],"(domain-agnostic)":[46],"or":[47],"instead":[48],"perform":[49],"zero-shot":[50],"(category-agnostic),":[53],"separately.":[54],"The":[55,77,138,164,183],"knowledge":[56],"gap":[57],"between":[58,126],"seen":[59,74,159,208],"unseen":[61,161,189,192],"poses":[64],"challenges":[65,86,97],"for":[66,106,108,170],"models":[67],"optimized":[68],"with":[69,90],"supervision":[70],"from":[71,191],"only":[73],"categories.":[76,163],"domain":[78,165,173],"difference":[79],"across":[80],"different":[81,91],"scenarios":[82],"also":[83],"causes":[84],"further":[85,168,179],"aligning":[88],"observations":[89],"appearances.":[92],"To":[93],"address":[94],"these":[95],"two":[96],"simultaneously,":[98],"we":[99],"propose":[100],"our":[101,217],"Instance":[102],"Dictionary":[103],"Learning":[104],"(IDL":[105],"short)":[107],"more":[109,146],"robust":[110],"accurate":[112],"performance.":[114],"We":[115],"first":[116],"design":[117],"a":[118,221],"pre-training":[119],"procedure":[120,181],"build":[122],"up":[123],"mappings":[125],"region":[127],"features":[128],"category":[130],"semantic":[131],"embeddings":[132],"by":[133],"introducing":[134],"instance":[135],"contrastive":[136],"learning.":[137],"joint":[139],"vision-semantic":[140],"space":[141],"is":[142,167,201],"formulated":[143],"through":[144],"detailed":[147],"instance-level":[148],"\u201cDictionary\u201d,":[149],"expresses":[151],"region-category":[153],"correspondences":[154],"helps":[156],"link":[157],"discrimination":[166],"designed":[169],"extracting":[171],"invariance":[174],"feature":[175],"representations":[176],"training":[180],"seamlessly.":[182],"proposed":[184],"IDL":[185],"could":[186,219],"domains":[193],"without":[194],"any":[195],"bounding":[196],"box":[197],"annotations":[198],"while":[199],"there":[200],"no":[202],"obvious":[203],"performance":[204,225],"drop":[205],"detecting":[207],"meanwhile.":[210],"Comprehensive":[211],"experiments":[212],"have":[213],"been":[214],"conducted":[215],"method":[218],"achieve":[220],"new":[222],"state-of-the-art":[223],"over":[226],"previous":[227],"algorithms.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}