{"id":"https://openalex.org/W3094171958","doi":"https://doi.org/10.1145/3340531.3412177","title":"Introduction to Computer Vision and Realtime Deep Learning-based Object Detection","display_name":"Introduction to Computer Vision and Realtime Deep Learning-based Object Detection","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094171958","doi":"https://doi.org/10.1145/3340531.3412177","mag":"3094171958"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","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/A5113808513","display_name":"James G. Shanahan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James G. Shanahan","raw_affiliation_strings":["Church and Duncan Group & University of California, Berkeley, San Francisco & Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Church and Duncan Group & University of California, Berkeley, San Francisco & Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113808513"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3515","last_page":"3516"},"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":0.993399977684021,"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":0.9919000267982483,"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":0.8693133592605591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7903286218643188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7795611619949341},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6126527786254883},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.5952938199043274},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5699489712715149},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5510488152503967},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5428639650344849},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.49144065380096436},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.47782400250434875},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46384766697883606},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44859588146209717},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.42857271432876587},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42850616574287415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2777237296104431},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.20491492748260498}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8693133592605591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903286218643188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7795611619949341},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6126527786254883},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.5952938199043274},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5699489712715149},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5510488152503967},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5428639650344849},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.49144065380096436},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.47782400250434875},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46384766697883606},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44859588146209717},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.42857271432876587},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42850616574287415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2777237296104431},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.20491492748260498},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340531.3412177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6200000047683716,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2125186487","https://openalex.org/W2561675875","https://openalex.org/W2613718673","https://openalex.org/W2795061970","https://openalex.org/W3018757597","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3204852000","https://openalex.org/W4205668735","https://openalex.org/W2901758161","https://openalex.org/W4297797959","https://openalex.org/W4297491714","https://openalex.org/W4387272257","https://openalex.org/W3114299475","https://openalex.org/W4312834249","https://openalex.org/W3108847140","https://openalex.org/W3209429418"],"abstract_inverted_index":{"The":[0],"main":[1],"focus":[2,177],"of":[3,7,21,30,47,115,137,158],"object":[4,29,42,83,139,180,194],"detection,":[5,60],"one":[6],"the":[8,72,103,113,135,175],"most":[9],"challenging":[10],"problems":[11,100],"in":[12,32,36,163,182,196],"computer":[13],"vision":[14],"(CV),":[15],"is":[16,178],"to":[17,82,88,125],"predict":[18],"a":[19,37,45,122,128,164],"set":[20],"bounding":[22],"boxes":[23],"and":[24,61,146,172,187],"category":[25],"labels":[26],"for":[27],"each":[28],"interest":[31],"an":[33],"image":[34],"or":[35],"point":[38,198],"cloud.":[39],"As":[40],"such,":[41],"detection":[43,84,140,161,181,195],"has":[44,65,108],"variety":[46],"exciting":[48],"downstream":[49],"applications":[50],"such":[51,101,142],"as":[52,102,143],"self-driving":[53],"cars,":[54],"checkout-less":[55],"shopping,":[56],"smart":[57],"cities,":[58],"cancer":[59],"more.":[62],"This":[63,131],"field":[64],"been":[66],"revolutionized":[67],"by":[68],"deep":[69],"learning":[70],"over":[71,112],"past":[73],"five":[74,116],"years,":[75],"where":[76],"during":[77],"this":[78,189],"time,":[79],"two-stage":[80,123],"approaches":[81,150],"have":[85],"given":[86],"way":[87],"simpler,":[89],"more":[90,148],"efficient,":[91],"one-stage":[92,129],"models.":[93],"Mean":[94],"average":[95],"precision":[96],"(mAP)":[97],"on":[98,179],"benchmark":[99],"COCO":[104],"Object":[105],"Detection":[106],"dataset":[107],"improved":[109],"almost":[110],"4X":[111],"course":[114],"years":[117],"from":[118,185],"15%":[119],"(Fast":[120],"RCNN,":[121],"approach)":[124],"55%":[126],"(EfficientDet7x,":[127],"approach).":[130],"tutorial":[132,190],"looks":[133],"under":[134],"hood":[136],"state-of-the-art":[138],"systems,":[141],"two-stage,":[144],"one-stage,":[145],"also":[147,192],"recent":[149],"based":[151],"upon":[152],"transformers.":[153],"It":[154],"builds":[155],"out":[156],"some":[157],"their":[159],"associated":[160],"pipelines":[162],"Jupyter":[165],"Notebook":[166],"using":[167],"Python,":[168],"OpenCV,":[169],"PyTorch,":[170],"Keras":[171],"Tensorflow.":[173],"While":[174],"primary":[176],"digital":[183],"images":[184],"cameras":[186],"videos,":[188],"will":[191],"introduce":[193],"3D":[197],"clouds.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}