{"id":"https://openalex.org/W4393371809","doi":"https://doi.org/10.1109/tcsvt.2024.3383914","title":"Integrating Language-Derived Appearance Elements With Visual Cues in Pedestrian Detection","display_name":"Integrating Language-Derived Appearance Elements With Visual Cues in Pedestrian Detection","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4393371809","doi":"https://doi.org/10.1109/tcsvt.2024.3383914"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3383914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3383914","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/A5103267187","display_name":"Sungjune Park","orcid":"https://orcid.org/0000-0003-4486-9026"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjune Park","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4486-9026","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046578258","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0000-0001-6524-8689"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6524-8689","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Lab, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0622,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92403537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"9","first_page":"7975","last_page":"7985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9664999842643738,"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":0.9664999842643738,"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/pedestrian","display_name":"Pedestrian","score":0.758105993270874},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.7104611992835999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5391291975975037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133887529373169},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4286131262779236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4022951126098633},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.33199796080589294},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24667814373970032},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14900290966033936},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.11448359489440918}],"concepts":[{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.758105993270874},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.7104611992835999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5391291975975037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133887529373169},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4286131262779236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4022951126098633},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33199796080589294},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24667814373970032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14900290966033936},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.11448359489440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3383914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3383914","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2027542261","https://openalex.org/W2081580037","https://openalex.org/W2154582212","https://openalex.org/W2194775991","https://openalex.org/W2344132218","https://openalex.org/W2428342532","https://openalex.org/W2753608104","https://openalex.org/W2895077992","https://openalex.org/W2902502320","https://openalex.org/W2916994131","https://openalex.org/W2941356874","https://openalex.org/W2943070176","https://openalex.org/W2970231061","https://openalex.org/W2973049837","https://openalex.org/W2997344726","https://openalex.org/W3033116542","https://openalex.org/W3034238904","https://openalex.org/W3082231033","https://openalex.org/W3090757175","https://openalex.org/W3130394099","https://openalex.org/W3138516171","https://openalex.org/W3158128549","https://openalex.org/W3161441544","https://openalex.org/W3172752666","https://openalex.org/W3173669596","https://openalex.org/W3194782062","https://openalex.org/W4214525587","https://openalex.org/W4221159372","https://openalex.org/W4226255121","https://openalex.org/W4230097545","https://openalex.org/W4312956471","https://openalex.org/W4313176063","https://openalex.org/W4313427326","https://openalex.org/W4315473444","https://openalex.org/W4321021726","https://openalex.org/W4321021961","https://openalex.org/W4323338501","https://openalex.org/W4323655724","https://openalex.org/W4377142736","https://openalex.org/W4379984073","https://openalex.org/W4382450236","https://openalex.org/W4385245566","https://openalex.org/W4385567015","https://openalex.org/W4385569741","https://openalex.org/W4386065569","https://openalex.org/W4386065596","https://openalex.org/W4386075937","https://openalex.org/W4386075969","https://openalex.org/W4386076314","https://openalex.org/W4386083115","https://openalex.org/W4394625869","https://openalex.org/W6750697433","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6784094891","https://openalex.org/W6784577980","https://openalex.org/W6791353385","https://openalex.org/W6802517928","https://openalex.org/W6802987763","https://openalex.org/W6810081322","https://openalex.org/W6810151762","https://openalex.org/W6839734537","https://openalex.org/W6850625674","https://openalex.org/W6852999659","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W2101960027","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W3122828758","https://openalex.org/W2170799233","https://openalex.org/W2972620127","https://openalex.org/W2981141433"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"their":[6],"capabilities":[7],"in":[8,33,82,99],"understanding":[9,34],"contextual":[10,35],"and":[11,38,80,93,119,204,213,232],"semantic":[12],"information":[13,180],"regarding":[14],"knowledge":[15,42,131,155,165],"of":[16,31,56,77,117,137,206],"instance":[17],"appearances.":[18],"In":[19],"this":[20,41,103],"paper,":[21],"we":[22,86,105,128,141,175,200],"introduce":[23],"a":[24,44,107,143,158,191],"novel":[25],"approach":[26],"to":[27,39,62,88,146,157,169],"utilize":[28],"the":[29,57,135,183,202],"strengths":[30],"LLMs":[32],"appearance":[36,91,130,138,148,154,179,185],"variations":[37],"leverage":[40],"into":[43],"vision":[45],"model":[46],"(here,":[47],"pedestrian":[48,51,100,160,198,221],"detection).":[49],"While":[50],"detection":[52,161,171,216,222],"is":[53,74],"considered":[54],"one":[55],"crucial":[58],"tasks":[59],"directly":[60],"related":[61],"our":[63,207],"safety":[64],"(":[65,224],"<italic":[66,225,229,233],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67,226,230,234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g</i>":[68],".,":[69,228],"intelligent":[70],"driving":[71],"systems),":[72],"it":[73],"challenging":[75],"because":[76],"varying":[78],"appearances":[79,116],"poses":[81],"diverse":[83],"scenes.":[84],"Therefore,":[85],"propose":[87],"formulate":[89],"language-derived":[90,184],"elements":[92,149,166,186],"incorporate":[94],"them":[95,124],"with":[96,187,196],"visual":[97,188],"cues":[98,189],"detection.":[101],"To":[102],"end,":[104],"establish":[106],"description":[108],"corpus":[109],"that":[110,133,174],"includes":[111],"numerous":[112],"narratives":[113],"describing":[114],"various":[115,170,197],"pedestrians":[118],"other":[120],"instances.":[121],"By":[122],"feeding":[123],"through":[125],"an":[126],"LLM,":[127],"extract":[129],"sets":[132],"contain":[134],"representations":[136],"variations.":[139],"Subsequently,":[140],"perform":[142],"task-prompting":[144],"process":[145],"obtain":[147],"which":[150],"are":[151,167],"guided":[152],"representative":[153],"relevant":[156],"downstream":[159],"task.":[162],"The":[163],"obtained":[164],"adaptable":[168],"frameworks,":[172],"so":[173],"can":[176],"provide":[177],"plentiful":[178],"by":[181],"integrating":[182],"within":[190],"detector.":[192],"Through":[193],"comprehensive":[194],"experiments":[195],"detectors,":[199],"verify":[201],"adaptability":[203],"effectiveness":[205],"method":[208],"showing":[209],"noticeable":[210],"performance":[211,217],"gains":[212],"achieving":[214],"state-of-the-art":[215],"on":[218],"two":[219],"public":[220],"benchmarks":[223],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e</i>":[227],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CrowdHuman</i>":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">WiderPedestrian</i>":[235],").":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}