{"id":"https://openalex.org/W3170768284","doi":"https://doi.org/10.1145/3447548.3467122","title":"Web-Scale Generic Object Detection at Microsoft Bing","display_name":"Web-Scale Generic Object Detection at Microsoft Bing","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3170768284","doi":"https://doi.org/10.1145/3447548.3467122","mag":"3170768284"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467122","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467122","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467122","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Stephen Xi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephen Xi Chen","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saurajit Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurajit Mukherjee","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Unmesh Phadke","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Unmesh Phadke","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tingting Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingting Wang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junwon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junwon Park","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ravi Theja Yada","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Theja Yada","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06199955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2674","last_page":"2682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.6935999989509583},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5859000086784363},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.49140000343322754},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3801000118255615},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3450999855995178},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162000179290771},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6935999989509583},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4964999854564667},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2741999924182892},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467122","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467122","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467122","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.01814","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01814","pdf_url":"https://arxiv.org/pdf/2107.01814","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467122","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467122","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467122","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3170768284.pdf","grobid_xml":"https://content.openalex.org/works/W3170768284.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2100142570","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2594696540","https://openalex.org/W2625758617","https://openalex.org/W2798687276","https://openalex.org/W2808965910","https://openalex.org/W2948672349","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963640793","https://openalex.org/W2963703197","https://openalex.org/W2966926453","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W2988916019","https://openalex.org/W3012573144","https://openalex.org/W3034933032","https://openalex.org/W3034971973","https://openalex.org/W3036463284","https://openalex.org/W3080750010"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,146],"present":[4],"Generic":[5],"Object":[6],"Detection":[7],"(GenOD),":[8],"one":[9],"of":[10,68],"the":[11,66,127,136],"largest":[12],"object":[13,78],"detection":[14,79],"systems":[15],"deployed":[16],"to":[17,120,142],"a":[18,43,76,86],"web-scale":[19],"general":[20],"visual":[21,45,151],"search":[22,152,158],"engine":[23],"that":[24,49,90,109],"can":[25,111],"detect":[26],"over":[27,117],"900":[28],"categories":[29],"for":[30],"all":[31],"Microsoft":[32],"Bing":[33],"Visual":[34],"Search":[35],"queries":[36],"in":[37,56],"near":[38],"real-time.":[39],"It":[40],"acts":[41],"as":[42],"fundamental":[44],"query":[46],"understanding":[47],"service":[48],"provides":[50],"object-centric":[51],"information":[52],"and":[53,73,98,162],"shows":[54],"gains":[55],"multiple":[57,82,121],"production":[58],"scenarios,":[59],"improving":[60,103,156],"upon":[61],"domain-specific":[62,122],"models.":[63,123],"We":[64,84,107,124],"discuss":[65,85],"challenges":[67],"collecting":[69],"data,":[70],"training,":[71],"deploying":[72],"updating":[74],"such":[75],"large-scale":[77],"model":[80,128],"with":[81,135],"dependencies.":[83],"data":[87],"collection":[88],"pipeline":[89],"reduces":[91],"per-bounding":[92],"box":[93],"labeling":[94],"cost":[95],"by":[96,100,116,131,154,160,165],"81.5%":[97],"latency":[99],"61.2%":[101],"while":[102],"on":[104],"annotation":[105],"quality.":[106],"show":[108],"GenOD":[110,149],"improve":[112,126],"weighted":[113],"average":[114],"precision":[115],"20%":[118],"compared":[119,141],"also":[125],"update":[129],"agility":[130],"nearly":[132],"2":[133],"times":[134],"proposed":[137],"disjoint":[138],"detector":[139],"training":[140],"joint":[143],"fine-tuning.":[144],"Finally":[145],"demonstrate":[147],"how":[148],"benefits":[150],"applications":[153],"significantly":[155],"object-level":[157],"relevance":[159],"54.9%":[161],"user":[163],"engagement":[164],"59.9%.":[166]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-06-22T00:00:00"}