{"id":"https://openalex.org/W4386598489","doi":"https://doi.org/10.1109/icip49359.2023.10223065","title":"DF-Net: Diversity-Focused Network for Video Object Detection","display_name":"DF-Net: Diversity-Focused Network for Video Object Detection","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598489","doi":"https://doi.org/10.1109/icip49359.2023.10223065"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223065","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10223065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018426248","display_name":"Zhenyu Qiu","orcid":"https://orcid.org/0000-0002-1679-7750"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Qiu","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072002612","display_name":"Qiang Qi","orcid":"https://orcid.org/0000-0002-9127-3404"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Qi","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2105","last_page":"2109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9984999895095825,"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":0.791398286819458},{"id":"https://openalex.org/keywords/deblurring","display_name":"Deblurring","score":0.6127367615699768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6124418377876282},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.570665717124939},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5680060982704163},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5579929947853088},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.538513720035553},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.53816819190979},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5081512928009033},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5073603987693787},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4833914339542389},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48064959049224854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46010980010032654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28489863872528076},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.21822094917297363},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.11516544222831726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09481176733970642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791398286819458},{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.6127367615699768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6124418377876282},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.570665717124939},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5680060982704163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5579929947853088},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.538513720035553},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.53816819190979},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5081512928009033},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5073603987693787},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4833914339542389},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48064959049224854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46010980010032654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28489863872528076},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.21822094917297363},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.11516544222831726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09481176733970642},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10223065","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10223065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8055606312","display_name":"\u57fa\u4e8e\u9c81\u68d2\u6a21\u578b\u62df\u5408\u548c\u6df1\u5ea6\u5b66\u4e60\u7684\u4eba\u8138\u5c5e\u6027\u8bc6\u522b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071404","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":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2117539524","https://openalex.org/W2222512263","https://openalex.org/W2336589871","https://openalex.org/W2552900565","https://openalex.org/W2898044248","https://openalex.org/W2964286567","https://openalex.org/W2970160757","https://openalex.org/W2970370255","https://openalex.org/W2994810768","https://openalex.org/W2996794639","https://openalex.org/W3034467781","https://openalex.org/W3096831136","https://openalex.org/W3103358580","https://openalex.org/W3206836360","https://openalex.org/W4212912983","https://openalex.org/W4285203457","https://openalex.org/W4285249134","https://openalex.org/W4293437100","https://openalex.org/W4308236037","https://openalex.org/W4317795300","https://openalex.org/W6779823529","https://openalex.org/W6795288823"],"related_works":["https://openalex.org/W4308216825","https://openalex.org/W4312281738","https://openalex.org/W2062923025","https://openalex.org/W2786875726","https://openalex.org/W3134004915","https://openalex.org/W2894651257","https://openalex.org/W3120085233","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"Video":[0],"object":[1,10],"detection":[2,47],"is":[3,18,70,98,120],"a":[4,51,87,109],"challenging":[5],"task":[6],"due":[7,40],"to":[8,19,41,72,100,104,122],"deteriorated":[9],"appearances.":[11],"To":[12],"enhance":[13],"per-frame":[14],"features,":[15],"one":[16],"way":[17],"aggregate":[20],"features":[21,125],"from":[22],"several":[23],"support":[24],"frames.":[25],"However,":[26],"proposals":[27,106],"generated":[28],"by":[29,86],"the":[30,42,46,74,79,102,105,124,139,147],"region":[31],"proposal":[32],"network":[33],"may":[34],"not":[35],"be":[36],"precise":[37],"and":[38,77,128],"diverse":[39],"fixed":[43],"anchors,":[44],"limiting":[45],"performance.":[48],"We":[49],"propose":[50],"novel":[52],"architecture":[53],"called":[54],"Diversity-Focused":[55],"Network":[56],"(DF-Net),":[57],"which":[58,69,97,119],"consists":[59],"of":[60,82,126],"three":[61],"modules:":[62],"1)":[63],"An":[64],"affine":[65],"transform":[66],"module":[67,95,117],"(ATM),":[68],"proposed":[71,99,121],"model":[73],"deblurring":[75],"process":[76],"fuse":[78],"feature":[80],"maps":[81],"different":[83],"receptive":[84],"fields":[85],"multi-level":[88],"attention":[89],"block;":[90],"2)":[91],"A":[92,114],"label":[93],"assignment":[94],"(LAM),":[96],"assign":[101],"labels":[103],"used":[107],"in":[108],"fine-grained":[110],"aggregation":[111],"manner;":[112],"3)":[113],"regression-guided":[115],"diffusion":[116],"(RGDM),":[118],"obtain":[123],"diversity":[127],"higher":[129],"quality.":[130],"Experiments":[131],"show":[132],"that":[133],"DF-Net":[134,148],"achieves":[135,149],"favorable":[136],"results":[137],"on":[138],"most":[140],"representative":[141],"large-scale":[142],"ImageNet":[143],"VID":[144],"dataset.":[145],"Remarkably,":[146],"84.8%":[150],"mAP":[151],"with":[152],"ResNet-101":[153],"without":[154],"post-processing":[155],"steps.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}