{"id":"https://openalex.org/W2125458485","doi":"https://doi.org/10.1109/icip.2009.5413922","title":"Face detection directly from h.264 compressed video with convolutional neural network","display_name":"Face detection directly from h.264 compressed video with convolutional neural network","publication_year":2009,"publication_date":"2009-11-01","ids":{"openalex":"https://openalex.org/W2125458485","doi":"https://doi.org/10.1109/icip.2009.5413922","mag":"2125458485"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2009.5413922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2009.5413922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 16th 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/A5004154718","display_name":"Shin-Shan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shin-Shan Zhuang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073849580","display_name":"Shang\u2010Hong Lai","orcid":"https://orcid.org/0000-0002-5092-993X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Hong Lai","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2485","last_page":"2488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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":0.9987000226974487,"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/T11448","display_name":"Face recognition and analysis","score":0.9983000159263611,"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":0.8247932195663452},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7901042699813843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7518512010574341},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6779218912124634},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.581323504447937},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5575369000434875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5222564339637756},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.49866533279418945},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4613511562347412},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.4583112895488739},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.45376622676849365},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.43845948576927185},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.34200045466423035},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19699841737747192},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18360647559165955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1078794002532959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247932195663452},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7901042699813843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7518512010574341},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6779218912124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.581323504447937},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5575369000434875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5222564339637756},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.49866533279418945},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4613511562347412},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.4583112895488739},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.45376622676849365},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.43845948576927185},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.34200045466423035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19699841737747192},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18360647559165955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1078794002532959},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2009.5413922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2009.5413922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 16th IEEE International Conference on Image Processing (ICIP)","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":10,"referenced_works":["https://openalex.org/W2116331921","https://openalex.org/W2120284346","https://openalex.org/W2124351082","https://openalex.org/W2133671888","https://openalex.org/W2147372797","https://openalex.org/W2159686933","https://openalex.org/W2217896605","https://openalex.org/W3097096317","https://openalex.org/W6677645242","https://openalex.org/W6681812861"],"related_works":["https://openalex.org/W2094583657","https://openalex.org/W1594300462","https://openalex.org/W2158009109","https://openalex.org/W1606460848","https://openalex.org/W1706111048","https://openalex.org/W2129927873","https://openalex.org/W2772846670","https://openalex.org/W2112852877","https://openalex.org/W2034796835","https://openalex.org/W3188631569"],"abstract_inverted_index":{"Human":[0],"faces":[1,42],"provide":[2],"a":[3,15,22],"useful":[4],"cue":[5],"in":[6,34,44,56],"indexing":[7],"video":[8,35,90],"content.":[9],"In":[10],"this":[11],"paper,":[12],"we":[13,48,93],"propose":[14],"novel":[16],"face":[17,32,65,86,110,118],"detection":[18],"algorithm":[19],"based":[20],"on":[21,120],"convolutional":[23],"neural":[24],"network":[25],"architecture":[26],"that":[27],"can":[28,94],"rapidly":[29],"detect":[30],"human":[31],"regions":[33],"sequences":[36],"encoded":[37],"by":[38],"H.264/AVC.":[39],"By":[40],"detecting":[41],"directly":[43],"the":[45,50,61,79,85,89,96,105,109,117,121,130,133],"compressed":[46],"domain,":[47],"use":[49],"discrete":[51],"cosine":[52],"transform":[53,77],"(DCT)":[54],"coefficients":[55],"H.264":[57,122],"intra":[58,123],"coding":[59,97],"as":[60],"feature":[62],"vector":[63],"for":[64],"detection,":[66],"thus":[67],"it":[68],"is":[69],"not":[70],"necessary":[71],"to":[72,104,108,128],"carry":[73],"out":[74],"additional":[75],"DCT":[76],"during":[78],"encoding":[80,91],"or":[81],"decoding":[82],"process.":[83],"With":[84],"detector":[87,119],"inside":[88],"process,":[92],"adjust":[95],"parameters":[98],"adaptively":[99],"and":[100],"allocate":[101],"more":[102],"resources":[103],"macroblocks":[106],"corresponding":[107],"regions.":[111],"Some":[112],"experimental":[113],"results":[114],"of":[115,132],"applying":[116],"coded":[124],"images":[125],"are":[126],"given":[127],"demonstrate":[129],"performance":[131],"proposed":[134],"algorithm.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}