{"id":"https://openalex.org/W3035219540","doi":"https://doi.org/10.1109/icme46284.2020.9102955","title":"Fianet: Video Object Detection Via Joint Feature-Level And Instance-Level Aggregation","display_name":"Fianet: Video Object Detection Via Joint Feature-Level And Instance-Level Aggregation","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3035219540","doi":"https://doi.org/10.1109/icme46284.2020.9102955","mag":"3035219540"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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/A5002397632","display_name":"Zhengshuai Wang","orcid":"https://orcid.org/0000-0001-5987-2039"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengshuai Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, 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/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, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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/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, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002397632"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3791591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7911784648895264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7345030307769775},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7316783666610718},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7011663913726807},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6878458261489868},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.618054211139679},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6004352569580078},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5779760479927063},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5277842879295349},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5031117796897888},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48507824540138245},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45844531059265137},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.42648184299468994},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.065562903881073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911784648895264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7345030307769775},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7316783666610718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7011663913726807},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6878458261489868},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.618054211139679},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6004352569580078},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5779760479927063},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5277842879295349},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5031117796897888},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48507824540138245},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45844531059265137},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.42648184299468994},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.065562903881073},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W2194775991","https://openalex.org/W2282391807","https://openalex.org/W2335901184","https://openalex.org/W2336589871","https://openalex.org/W2407521645","https://openalex.org/W2552900565","https://openalex.org/W2613718673","https://openalex.org/W2793130599","https://openalex.org/W2796347433","https://openalex.org/W2898044248","https://openalex.org/W2950800384","https://openalex.org/W2962855257","https://openalex.org/W2963212638","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W2971320590","https://openalex.org/W3100935401","https://openalex.org/W4293437100","https://openalex.org/W4293584584","https://openalex.org/W6620707391","https://openalex.org/W6695799263","https://openalex.org/W6714138976","https://openalex.org/W6746472748","https://openalex.org/W6750227808","https://openalex.org/W6755600014"],"related_works":["https://openalex.org/W3135697610","https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W2922442631","https://openalex.org/W4390494008","https://openalex.org/W2053596378","https://openalex.org/W2168523118","https://openalex.org/W2073639911"],"abstract_inverted_index":{"Video":[0],"object":[1,57],"detection":[2,58],"task":[3],"is":[4,129],"challenging":[5],"due":[6],"to":[7,23,40,80,106],"the":[8,18,82,90],"nonrigid":[9],"and":[10,32,46,64,95,100,134],"rigid":[11,41],"appearance":[12],"deformations":[13,42],"in":[14],"videos.":[15],"Most":[16],"of":[17,30,92],"typical":[19],"competitive":[20],"methods":[21],"are":[22],"enhance":[24],"per-frame":[25],"features":[26],"through":[27],"aggregating":[28],"lots":[29],"previous":[31,113],"future":[33],"frames.":[34],"But":[35],"feature-level":[36,62,70],"aggregation":[37,63,66,102],"isn't":[38],"robust":[39],"such":[43],"as":[44,84],"occlusion":[45],"rare":[47],"postures.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,72],"propose":[53],"an":[54],"online":[55],"video":[56],"method":[59,116],"with":[60,121,132],"joint":[61],"instance-level":[65,101],"network":[67],"(FIANet).":[68],"Besides":[69],"aggregation,":[71],"design":[73],"a":[74,85],"spatial-temporal":[75],"instance":[76,83],"calibration":[77],"module":[78],"(STIC)":[79],"aggregate":[81],"whole,":[86],"which":[87,128],"can":[88,103,117],"reduce":[89],"interference":[91],"local":[93],"distorted":[94],"missed":[96],"pixels.":[97],"Joint":[98],"featurelevel":[99],"work":[104],"collaboratively":[105],"overcome":[107],"different":[108],"deformations.":[109],"Only":[110],"using":[111],"less":[112],"frames,":[114],"our":[115],"achieve":[118],"81.6%":[119],"mAP":[120],"relatively":[122],"high":[123],"speed":[124],"on":[125],"ImageNet":[126],"VID,":[127],"state-of-the-art":[130],"compared":[131],"causal":[133],"non-causal":[135],"methods.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}