{"id":"https://openalex.org/W4387969399","doi":"https://doi.org/10.1145/3581783.3612342","title":"Patch-Aware Representation Learning for Facial Expression Recognition","display_name":"Patch-Aware Representation Learning for Facial Expression Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969399","doi":"https://doi.org/10.1145/3581783.3612342"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612342","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5108056167","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0002-2565-6482"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077046519","display_name":"Shangfei Wang","orcid":"https://orcid.org/0000-0003-1164-9895"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangfei Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039168974","display_name":"Yanan Chang","orcid":"https://orcid.org/0000-0001-7338-5544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Chang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108056167"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.308,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81242867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6143","last_page":"6151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"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/T11448","display_name":"Face recognition and analysis","score":0.9983999729156494,"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":0.7623245716094971},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7193045020103455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6949249505996704},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6801556348800659},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6536966562271118},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6270273923873901},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5531969666481018},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5426287651062012},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.49767735600471497},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4909422695636749},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4772738814353943},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.2795543372631073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623245716094971},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7193045020103455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6949249505996704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6801556348800659},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6536966562271118},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6270273923873901},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5531969666481018},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5426287651062012},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.49767735600471497},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4909422695636749},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4772738814353943},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2795543372631073},{"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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612342","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1979377847","https://openalex.org/W2014185685","https://openalex.org/W2106390385","https://openalex.org/W2194775991","https://openalex.org/W2487852963","https://openalex.org/W2738672149","https://openalex.org/W2770121394","https://openalex.org/W2798553619","https://openalex.org/W2805613995","https://openalex.org/W2805781993","https://openalex.org/W2904483377","https://openalex.org/W2982153880","https://openalex.org/W2982204884","https://openalex.org/W3003720578","https://openalex.org/W3006012949","https://openalex.org/W3035336958","https://openalex.org/W3035382243","https://openalex.org/W3093232475","https://openalex.org/W3118530108","https://openalex.org/W3154541964","https://openalex.org/W3195286673","https://openalex.org/W3209798173","https://openalex.org/W4285784163","https://openalex.org/W4311414773","https://openalex.org/W4313156423","https://openalex.org/W4403242122"],"related_works":["https://openalex.org/W4205986151","https://openalex.org/W2355913164","https://openalex.org/W2162992774","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2116055069","https://openalex.org/W4323520705","https://openalex.org/W2356663679","https://openalex.org/W2169777806","https://openalex.org/W3027190010"],"abstract_inverted_index":{"Existing":[0],"methods":[1],"for":[2],"facial":[3,12,34,52,58,64,116,215],"expression":[4],"recognition":[5],"(FER)":[6],"lack":[7],"the":[8,38,63,72,82,110,115,129,140,146,151,162,172,178,186,189,194,200,204,213,226],"utilization":[9],"of":[10],"prior":[11],"knowledge,":[13],"primarily":[14],"focusing":[15],"on":[16,220],"expression-related":[17,133],"regions":[18,195],"while":[19,199],"disregarding":[20],"explicitly":[21],"processing":[22],"expression-independent":[23,209],"information.":[24],"This":[25],"paper":[26],"proposes":[27],"a":[28,57,77,87,99,119,182],"patch-aware":[29],"FER":[30],"method":[31,228],"that":[32,225],"incorporates":[33],"keypoints":[35,53,83],"to":[36,98,109,131,144,160,197,206],"guide":[37],"model":[39],"and":[40,62,84,142,149,174,217],"learns":[41,191],"precise":[42],"representations":[43],"through":[44,139],"two":[45,221],"collaborative":[46,92],"streams,":[47],"addressing":[48],"these":[49],"issues.":[50],"First,":[51],"are":[54,94,137],"detected":[55],"using":[56,71,86],"landmark":[59],"detection":[60],"algorithm,":[61],"image":[65,124,167],"is":[66,79,126,169],"divided":[67],"into":[68,128,171],"equal-sized":[69],"patches":[70,85,107,148,158],"Patch":[73],"Embedding":[74],"Module.":[75],"Then,":[76],"correlation":[78],"established":[80],"between":[81],"simplified":[88],"conversion":[89],"relationship.":[90],"Two":[91],"streams":[93],"introduced,":[95],"each":[96],"corresponding":[97,108,159],"specific":[100],"mask":[101],"strategy.":[102],"The":[103,122,135,154,165],"first":[104,187],"stream":[105,156,202],"masks":[106,157],"keypoints,":[111],"excluding":[112],"those":[113],"along":[114],"contour,":[117],"with":[118,177],"certain":[120],"probability.":[121],"resulting":[123,166,179],"embedding":[125,168],"input":[127,170],"Encoder":[130,173,190,205],"obtain":[132],"features.":[134],"features":[136,192],"passed":[138],"Decoder":[141],"Classifier":[143,175],"reconstruct":[145],"masked":[147],"recognize":[150],"expression,":[152,198],"respectively.":[153],"second":[155,201],"all":[161],"above":[163],"keypoints.":[164],"successively,":[176],"logit":[180],"approximating":[181],"uniform":[183],"distribution.":[184],"Through":[185],"stream,":[188],"in":[193],"related":[196],"enables":[203],"better":[207],"ignore":[208],"information,":[210],"such":[211],"as":[212],"background,":[214],"contours,":[216],"hair.":[218],"Experiments":[219],"benchmark":[222],"datasets":[223],"demonstrate":[224],"proposed":[227],"outperforms":[229],"state-of-the-art":[230],"methods.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}