{"id":"https://openalex.org/W7147149119","doi":"https://doi.org/10.1109/icvisp68610.2025.11451735","title":"DFVNet: Density Feature Guided Small Object Detection in Video","display_name":"DFVNet: Density Feature Guided Small Object Detection in Video","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W7147149119","doi":"https://doi.org/10.1109/icvisp68610.2025.11451735"},"language":null,"primary_location":{"id":"doi:10.1109/icvisp68610.2025.11451735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icvisp68610.2025.11451735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Conference on Vision, Image and Signal Processing (ICVISP)","raw_type":"proceedings-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/A5132715001","display_name":"Junhe Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junhe Lv","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132646749","display_name":"Linwei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linwei Chen","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132721751","display_name":"Ying Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Fu","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132722416","display_name":"Jun Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151935","display_name":"Dahua Technology (China)","ror":"https://ror.org/04k9ktn61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yin","raw_affiliation_strings":["Zhejiang Dahua Technology Co., Ltd.,Institute of Advanced Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Dahua Technology Co., Ltd.,Institute of Advanced Technology,Hangzhou,China","institution_ids":["https://openalex.org/I4210151935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031463171","display_name":"Yayun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151935","display_name":"Dahua Technology (China)","ror":"https://ror.org/04k9ktn61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayun Wang","raw_affiliation_strings":["Zhejiang Dahua Technology Co., Ltd.,Institute of Advanced Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Dahua Technology Co., Ltd.,Institute of Advanced Technology,Hangzhou,China","institution_ids":["https://openalex.org/I4210151935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132556272","display_name":"Chenggang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["Hangzhou Dianzi University,School of Communication Engineering,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Communication Engineering,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132715001"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7488041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7735000252723694,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7735000252723694,"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":0.06159999966621399,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03099999949336052,"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/object-detection","display_name":"Object detection","score":0.7508999705314636},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.5011000037193298},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4442000091075897},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.4230000078678131},{"id":"https://openalex.org/keywords/motion-detection","display_name":"Motion detection","score":0.41119998693466187},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4041999876499176},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3952000141143799}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7602999806404114},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7508999705314636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325000166893005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6916000247001648},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.5011000037193298},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.41119998693466187},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3871999979019165},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2768999934196472},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.2615000009536743},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icvisp68610.2025.11451735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icvisp68610.2025.11451735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Conference on Vision, Image and Signal Processing (ICVISP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2565639579","https://openalex.org/W2964241181","https://openalex.org/W3034467781","https://openalex.org/W3042421830","https://openalex.org/W3096609285","https://openalex.org/W3121020412","https://openalex.org/W3186573928","https://openalex.org/W3205100603","https://openalex.org/W4221166276","https://openalex.org/W4320002812","https://openalex.org/W4382469019","https://openalex.org/W4386071826","https://openalex.org/W4387063747","https://openalex.org/W4392172931","https://openalex.org/W4396629505","https://openalex.org/W4400876843","https://openalex.org/W4400876894","https://openalex.org/W4401879614","https://openalex.org/W4402702923","https://openalex.org/W4402754006","https://openalex.org/W4403888306","https://openalex.org/W4412623660","https://openalex.org/W4413144865"],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"small":[1,19,77],"objects":[2],"is":[3],"a":[4,68,98],"critical":[5],"task":[6],"in":[7,53,57],"various":[8],"application":[9],"domains,":[10],"including":[11],"autonomous":[12],"driving":[13],"and":[14,42,91,131],"drone":[15],"recognition.":[16],"However,":[17],"existing":[18],"object":[20,78],"detection":[21,59,95,129,137],"methods,":[22],"which":[23],"are":[24],"predominantly":[25],"based":[26],"on":[27,111],"single":[28],"images,":[29],"often":[30],"fail":[31],"to":[32,37,84,127],"capture":[33],"essential":[34],"information":[35,86],"due":[36],"issues":[38],"such":[39],"as":[40],"density":[41,82],"motion":[43],"blur.":[44],"These":[45],"methods":[46,130],"also":[47],"neglect":[48],"the":[49,93,112],"temporal":[50,107],"context":[51],"inherent":[52],"real-world":[54],"scenarios,":[55],"resulting":[56],"suboptimal":[58],"performance.":[60],"To":[61],"address":[62],"these":[63],"limitations,":[64],"this":[65],"paper":[66],"proposes":[67],"novel":[69],"video-based":[70,136],"Detection":[71],"Transformer":[72],"Network,":[73],"named":[74],"DFVNet,":[75],"for":[76],"detection.":[79],"DFVNet":[80,117],"leverages":[81],"features":[83,104],"extract":[85],"from":[87,105],"densely":[88],"packed":[89],"s":[90],"enhances":[92],"current":[94],"frame":[96],"through":[97],"coarse-to-fine":[99],"refinement":[100],"process,":[101],"utilizing":[102],"reference":[103],"adjacent":[106],"frames.":[108],"Extensive":[109],"experiments":[110],"VisDrone2019-VID":[113],"dataset":[114],"show":[115],"that":[116],"improves":[118],"average":[119],"precision":[120],"AP<inf":[121],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">50</inf>":[123],"by":[124,132],"3.0%":[125],"compared":[126],"image-based":[128],"4.1%":[133],"over":[134],"other":[135],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-02T00:00:00"}