{"id":"https://openalex.org/W2146290679","doi":"https://doi.org/10.1109/icme.2009.5202435","title":"Video coding based on audio-visual attention","display_name":"Video coding based on audio-visual attention","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2146290679","doi":"https://doi.org/10.1109/icme.2009.5202435","mag":"2146290679"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2009.5202435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/134765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668167","display_name":"Jong\u2010Seok Lee","orcid":"https://orcid.org/0000-0002-8038-1119"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jong-Seok Lee","raw_affiliation_strings":["Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005876625","display_name":"F. Simone","orcid":"https://orcid.org/0000-0001-5272-9221"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Francesca De Simone","raw_affiliation_strings":["Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082188773","display_name":"Touradj Ebrahimi","orcid":"https://orcid.org/0000-0002-9900-3687"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Touradj Ebrahimi","raw_affiliation_strings":["Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Multimedia Signal Processing Group, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100668167"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":2.4997,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8948939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9958000183105469,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9922000169754028,"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":0.8322674036026001},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6861975789070129},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6543000340461731},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5053227543830872},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49322789907455444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48094457387924194},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45380571484565735},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.4366675615310669},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4218143820762634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40891557931900024},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.18729451298713684},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.1648656725883484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322674036026001},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6861975789070129},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6543000340461731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5053227543830872},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49322789907455444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48094457387924194},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45380571484565735},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.4366675615310669},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4218143820762634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40891557931900024},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.18729451298713684},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.1648656725883484},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icme.2009.5202435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.1875","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.1875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/134765/files/lee09_icme.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:134765","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/134765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:134765","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/35922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:134765","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/134765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1976764766","https://openalex.org/W1977385101","https://openalex.org/W2015394094","https://openalex.org/W2017460840","https://openalex.org/W2042608483","https://openalex.org/W2052218491","https://openalex.org/W2079028795","https://openalex.org/W2098923380","https://openalex.org/W2099151709","https://openalex.org/W2130184867","https://openalex.org/W2134867751","https://openalex.org/W2137446410","https://openalex.org/W2137968810","https://openalex.org/W2142352693","https://openalex.org/W2154496665","https://openalex.org/W2160881085","https://openalex.org/W2165081189","https://openalex.org/W2170326347"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2019123532","https://openalex.org/W2034819097","https://openalex.org/W2120007390","https://openalex.org/W2908833932","https://openalex.org/W2467977993","https://openalex.org/W1579233721","https://openalex.org/W2167514117"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,31],"efficient":[4],"video":[5,43,55],"coding":[6,66,78],"method":[7,35,75],"based":[8],"on":[9],"audio-visual":[10,32],"attention,":[11],"which":[12],"is":[13,48],"motivated":[14],"by":[15],"the":[16,38,70,73,81],"fact":[17],"that":[18],"cross-modal":[19],"interaction":[20],"significantly":[21],"affects":[22],"humans'":[23],"perception":[24],"of":[25,72,83],"multimedia":[26],"content.":[27],"First,":[28],"we":[29],"propose":[30],"source":[33,40],"localization":[34],"to":[36,54,59],"locate":[37],"sound":[39],"in":[41,57],"a":[42,84],"sequence.":[44],"Then,":[45],"its":[46],"result":[47],"used":[49],"for":[50,76],"applying":[51],"spatial":[52],"blurring":[53],"frames":[56],"order":[58],"reduce":[60],"redundant":[61],"high-frequency":[62],"information":[63],"and":[64],"achieve":[65],"efficiency.":[67],"We":[68],"demonstrate":[69],"effectiveness":[71],"proposed":[74],"H.264/AVC":[77],"along":[79],"with":[80],"results":[82],"subjective":[85],"evaluation.":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
