{"id":"https://openalex.org/W4403780494","doi":"https://doi.org/10.1145/3664647.3688986","title":"Towards Engagement Prediction: A Cross-Modality Dual-Pipeline Approach using Visual and Audio Features","display_name":"Towards Engagement Prediction: A Cross-Modality Dual-Pipeline Approach using Visual and Audio Features","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780494","doi":"https://doi.org/10.1145/3664647.3688986"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688986","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3688986","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101605304","display_name":"Deepak Kumar","orcid":"https://orcid.org/0000-0002-8622-7251"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Kumar","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India"],"raw_orcid":"https://orcid.org/0000-0002-8622-7251","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078144481","display_name":"Surbhi Madan","orcid":"https://orcid.org/0009-0000-3774-8117"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Surbhi Madan","raw_affiliation_strings":["Indian Institute of Technology Ropar, Rupnagar, Punjab, India"],"raw_orcid":"https://orcid.org/0009-0000-3774-8117","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, Rupnagar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780181","display_name":"Pradeep Singh","orcid":"https://orcid.org/0000-0002-5372-3355"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pradeep Singh","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India"],"raw_orcid":"https://orcid.org/0000-0002-5372-3355","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abhinav Dhall","raw_affiliation_strings":["Flinders University & Indian Institute of Technology Ropar, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2230-1440","affiliations":[{"raw_affiliation_string":"Flinders University & Indian Institute of Technology Ropar, Adelaide, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030765476","display_name":"Balasubramanian Raman","orcid":"https://orcid.org/0000-0001-6277-6267"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balasubramanian Raman","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India"],"raw_orcid":"https://orcid.org/0000-0001-6277-6267","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5286,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83804123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11383","last_page":"11389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9939000010490417,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926000237464905,"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/audio-visual","display_name":"Audio visual","score":0.7611993551254272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7213630676269531},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6874223947525024},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6099934577941895},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5884081125259399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42336583137512207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3527200520038605},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3392869830131531},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2834514081478119},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14107131958007812},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07918307185173035}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7611993551254272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213630676269531},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6874223947525024},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6099934577941895},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5884081125259399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42336583137512207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3527200520038605},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3392869830131531},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2834514081478119},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14107131958007812},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07918307185173035},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688986","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3688986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688986","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2081112272","https://openalex.org/W2143926884","https://openalex.org/W2239141610","https://openalex.org/W2395639500","https://openalex.org/W2590255117","https://openalex.org/W2619383789","https://openalex.org/W2755291975","https://openalex.org/W2782668511","https://openalex.org/W2786900386","https://openalex.org/W2806887026","https://openalex.org/W2964051877","https://openalex.org/W2980987964","https://openalex.org/W2995682556","https://openalex.org/W3101726544","https://openalex.org/W3205504809","https://openalex.org/W3206659986","https://openalex.org/W4288099396","https://openalex.org/W4296596271","https://openalex.org/W4385965696","https://openalex.org/W4386908203","https://openalex.org/W4387423980","https://openalex.org/W4387423997","https://openalex.org/W4387969083","https://openalex.org/W4387969647","https://openalex.org/W4388192187","https://openalex.org/W4402712443","https://openalex.org/W4402917158"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Engagement":[0],"estimation":[1,129],"is":[2],"crucial":[3],"for":[4],"advancing":[5],"natural":[6],"human-computer":[7],"interaction,":[8],"allowing":[9],"artificial":[10,192],"agents":[11],"to":[12,42,59,115,186],"dynamically":[13],"adjust":[14],"their":[15],"responses":[16],"based":[17],"on":[18,142],"user":[19,195],"engagement":[20,34,117,128,156],"levels":[21],"and":[22,26,71,84,98,121,135,145,148,190],"creating":[23],"more":[24,188],"intuitive":[25],"immersive":[27],"experiences.":[28],"Despite":[29],"advancements":[30],"in":[31,38,154],"automating":[32],"real-time":[33],"estimation,":[35],"challenges":[36,62],"persist":[37],"real-world":[39],"scenarios":[40],"due":[41],"the":[43,125,149,159,181],"complex":[44],"nature":[45,162],"of":[46,127,163],"multi-modal":[47,65],"human":[48,164],"social":[49],"signals.":[50],"This":[51,119,183],"paper":[52],"proposes":[53],"a":[54,92,101,170],"novel":[55],"cross-modality":[56],"fusion-based":[57],"methodology":[58],"address":[60],"these":[61],"by":[63,130],"leveraging":[64],"data.":[66],"Our":[67],"approach":[68,123,168],"integrates":[69],"visual":[70],"audio":[72],"features,":[73],"such":[74],"as":[75],"facial":[76],"motion,":[77],"acoustic":[78],"characteristics,":[79],"Contrastive":[80],"Language-Image":[81],"Pretraining":[82],"(CLIP),":[83],"semantic":[85],"embeddings.":[86],"These":[87],"features":[88,111],"first":[89],"pass":[90],"through":[91,100],"transformer":[93],"encoder,":[94],"are":[95,112,140],"then":[96,113],"combined":[97],"processed":[99],"cross-modal":[102],"fusion":[103],"mechanism,":[104],"ensuring":[105],"robust":[106],"integration.":[107],"The":[108,138],"final":[109],"integrated":[110],"used":[114],"predict":[116],"scores.":[118],"hierarchical":[120],"self-normalizing":[122],"enhances":[124],"accuracy":[126],"effectively":[131],"capturing":[132],"dependencies":[133],"within":[134],"between":[136],"modalities.":[137],"experiments":[139],"conducted":[141],"multimediate's":[143],"NoXI":[144],"MPIIGroupInteraction":[146],"datasets":[147],"results":[150],"demonstrates":[151],"competitive":[152],"performance":[153],"estimating":[155],"levels,":[157],"addressing":[158],"complex,":[160],"context-dependent":[161],"engagement.":[165],"Specifically,":[166],"our":[167],"achieves":[169],"Global":[171],"Concordance":[172],"Correlation":[173],"Coefficient":[174],"(CCC)":[175],"score":[176],"approximately":[177],"(56.1%)":[178],"higher":[179],"than":[180],"baseline.":[182],"work":[184],"contributes":[185],"developing":[187],"intelligent":[189],"responsive":[191],"systems,":[193],"enhancing":[194],"experiences":[196],"across":[197],"various":[198],"interactive":[199],"applications.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}