{"id":"https://openalex.org/W3167911833","doi":"https://doi.org/10.1109/icme51207.2021.9428181","title":"Modulating Localization and Classification for Harmonized Object Detection","display_name":"Modulating Localization and Classification for Harmonized Object Detection","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3167911833","doi":"https://doi.org/10.1109/icme51207.2021.9428181","mag":"3167911833"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5042977918","display_name":"Taiheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Taiheng Zhang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047098807","display_name":"Qiaoyong Zhong","orcid":"https://orcid.org/0000-0002-5944-1818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaoyong Zhong","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636142","display_name":"Di Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xie","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042977918"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36748366,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9966999888420105,"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":0.9940999746322632,"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":0.7768465280532837},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7596311569213867},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6997068524360657},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6384387016296387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251375675201416},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6202494502067566},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.5422452688217163},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5227230191230774},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.50662761926651},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4804617762565613},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.45661893486976624},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.45508816838264465},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4484545886516571},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43977296352386475},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14114409685134888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11107742786407471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768465280532837},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7596311569213867},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6997068524360657},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6384387016296387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251375675201416},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6202494502067566},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.5422452688217163},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5227230191230774},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.50662761926651},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4804617762565613},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.45661893486976624},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.45508816838264465},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4484545886516571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43977296352386475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14114409685134888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11107742786407471},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2129987527","https://openalex.org/W2133059825","https://openalex.org/W2194775991","https://openalex.org/W2504335775","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2578797046","https://openalex.org/W2620998106","https://openalex.org/W2886904239","https://openalex.org/W2899771611","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963497947","https://openalex.org/W2982770724","https://openalex.org/W3035395201","https://openalex.org/W3035396860","https://openalex.org/W3039009902","https://openalex.org/W3106250896","https://openalex.org/W3108849448","https://openalex.org/W4288325606","https://openalex.org/W4292402161","https://openalex.org/W4293584584","https://openalex.org/W6639102338","https://openalex.org/W6679461745","https://openalex.org/W6750227808","https://openalex.org/W6756040250","https://openalex.org/W6764322716","https://openalex.org/W6779990023","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4309997567","https://openalex.org/W2741875024","https://openalex.org/W2100227865","https://openalex.org/W3136779501","https://openalex.org/W3122044802","https://openalex.org/W2081167087","https://openalex.org/W2334467465","https://openalex.org/W2756666606","https://openalex.org/W1576256164","https://openalex.org/W4245194009"],"abstract_inverted_index":{"Object":[0],"detection":[1,100],"involves":[2],"two":[3,48,53],"sub-tasks,":[4],"i.e.":[5],"localizing":[6],"objects":[7],"in":[8,34],"an":[9],"image":[10],"and":[11,28,107,118],"classifying":[12],"them":[13],"into":[14,112],"various":[15],"categories.":[16],"For":[17],"existing":[18,113],"CNN-based":[19],"detectors,":[20],"we":[21,39,69,84],"notice":[22],"the":[23,47,52,81,93,99,127,131],"widespread":[24],"divergence":[25],"between":[26],"localization":[27],"classification,":[29],"which":[30,78,95],"leads":[31],"to":[32,45,57,91],"degradation":[33],"performance.":[35,101],"In":[36,50],"this":[37],"work,":[38],"propose":[40],"a":[41,63,71,86,122],"mutual":[42,65],"learning":[43],"framework":[44],"modulate":[46],"tasks.":[49],"particular,":[51],"tasks":[54],"are":[55],"forced":[56],"learn":[58],"from":[59],"each":[60],"other":[61],"with":[62,98],"novel":[64],"labeling":[66],"strategy.":[67],"Besides,":[68],"introduce":[70],"simple":[72],"yet":[73],"effective":[74],"IoU":[75],"rescoring":[76],"scheme,":[77],"further":[79],"reduces":[80],"divergence.":[82],"Moreover,":[83],"define":[85],"Spearman":[87],"rank":[88],"correlation-based":[89],"metric":[90],"quantify":[92],"divergence,":[94],"correlates":[96],"well":[97],"The":[102],"proposed":[103],"approach":[104],"is":[105],"general-purpose":[106],"can":[108],"be":[109],"easily":[110],"injected":[111],"detectors":[114,129],"such":[115],"as":[116],"FCOS":[117],"RetinaNet.":[119],"We":[120],"achieve":[121],"significant":[123],"performance":[124],"gain":[125],"over":[126],"baseline":[128],"on":[130],"COCO":[132],"dataset.":[133]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}