{"id":"https://openalex.org/W4405784968","doi":"https://doi.org/10.1109/iros58592.2024.10801375","title":"MLPER: Multi-Level Prompts for Adaptively Enhancing Vision-Language Emotion Recognition","display_name":"MLPER: Multi-Level Prompts for Adaptively Enhancing Vision-Language Emotion Recognition","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405784968","doi":"https://doi.org/10.1109/iros58592.2024.10801375"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5115591245","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0002-0286-6794"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Gao","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072203497","display_name":"Weihong Ren","orcid":"https://orcid.org/0000-0003-3839-0078"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihong Ren","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101093602","display_name":"Xinglong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglong Xu","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846033","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0003-4309-3166"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443923","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-3858-983X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114090968","display_name":"Honghai Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghai Liu","raw_affiliation_strings":["Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Mechanical Engineering and Automation, State Key Lab of Robotics and Systems,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115591245"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58080827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12640","last_page":"12647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9478999972343445,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9478999972343445,"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":0.9416999816894531,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9402999877929688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182115912437439},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.599649965763092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5126796960830688},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46712714433670044},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39666324853897095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3902529776096344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33208149671554565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182115912437439},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.599649965763092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126796960830688},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46712714433670044},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39666324853897095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3902529776096344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33208149671554565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2143238378","https://openalex.org/W2145310492","https://openalex.org/W2738672149","https://openalex.org/W2739474071","https://openalex.org/W2745497104","https://openalex.org/W2889978276","https://openalex.org/W2904483377","https://openalex.org/W2963712289","https://openalex.org/W2964751875","https://openalex.org/W3001529617","https://openalex.org/W3003720578","https://openalex.org/W3034520808","https://openalex.org/W3118405827","https://openalex.org/W3135844897","https://openalex.org/W3176899168","https://openalex.org/W3179103990","https://openalex.org/W3184134865","https://openalex.org/W3195286673","https://openalex.org/W3209798173","https://openalex.org/W4285606530","https://openalex.org/W4311414773","https://openalex.org/W4312438838","https://openalex.org/W4312465353","https://openalex.org/W4313194685","https://openalex.org/W4316660726","https://openalex.org/W4319300140","https://openalex.org/W4376278471","https://openalex.org/W4382450267","https://openalex.org/W4382460786","https://openalex.org/W4386075843","https://openalex.org/W4389665539","https://openalex.org/W4390871994","https://openalex.org/W4402979749","https://openalex.org/W6764733053","https://openalex.org/W6791353385","https://openalex.org/W6798838024","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"In":[0,31],"the":[1,17,89,95,113,116,141,150],"field":[2],"of":[3,19,61,127,152],"robotics,":[4],"vision-based":[5],"Emotion":[6,43],"Recognition":[7,44],"(ER)":[8],"has":[9],"achieved":[10],"significant":[11],"progress,":[12],"but":[13],"it":[14],"still":[15],"faces":[16],"challenge":[18],"poor":[20],"generalization":[21],"ability":[22],"under":[23,149],"unconstrained":[24],"conditions":[25,151],"(e.g.,":[26,58],"occlusions":[27,153],"and":[28,77,98,115,129,154],"pose":[29,155],"variations).":[30],"this":[32],"work,":[33],"we":[34,65,87,108],"propose":[35],"MLPER":[36,138],"model,":[37],"which":[38],"introduces":[39],"Vision-Language":[40],"Model":[41],"for":[42],"to":[45,101,119],"learn":[46],"discriminative":[47],"representations":[48],"adaptively.":[49],"Specifically,":[50],"different":[51],"from":[52,70,92,112],"typically":[53],"leveraging":[54],"a":[55,62,125],"hand-crafted":[56],"prompt":[57],"\"a":[59],"photo":[60],"[class]":[63],"person\"),":[64],"first":[66],"establish":[67],"Multi-Level":[68],"Prompts":[69],"three":[71,93],"aspects:":[72],"facial":[73],"expression,":[74],"human":[75],"posture":[76],"situational":[78],"condition":[79],"using":[80],"large":[81],"language":[82],"models,":[83],"like":[84],"ChatGPT.":[85],"Correspondingly,":[86],"extract":[88],"visual":[90,121],"tokens":[91,111],"levels:":[94],"face,":[96],"body,":[97],"context.":[99],"Further,":[100],"achieve":[102],"fine-grained":[103],"alignment":[104],"at":[105],"each":[106],"level,":[107],"adopt":[109],"textual":[110],"positive":[114],"hard":[117],"negative":[118],"query":[120],"tokens,":[122],"predicting":[123],"whether":[124],"pair":[126],"image":[128],"text":[130],"is":[131],"matched.":[132],"Experimental":[133],"results":[134],"demonstrate":[135],"that":[136],"our":[137],"model":[139],"outperforms":[140],"state-of-the-art":[142],"methods":[143],"on":[144],"several":[145],"ER":[146],"benchmarks,":[147],"especially":[148],"variations.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}