{"id":"https://openalex.org/W7166860065","doi":"https://doi.org/10.18653/v1/2026.acl-long.171","title":"Open Your Model\u2019s Eyes: Video and Context-Aware Multimodal Backchannel Prediction","display_name":"Open Your Model\u2019s Eyes: Video and Context-Aware Multimodal Backchannel Prediction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166860065","doi":"https://doi.org/10.18653/v1/2026.acl-long.171"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.171","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100340248","display_name":"Minjae Kim","orcid":"https://orcid.org/0000-0001-8746-1915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min-Jae Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760640","display_name":"Jun-Yeong Moon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun-Yeong Moon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139844920","display_name":"Mujeen Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mujeen Sung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139725371","display_name":"Gyeong-Moon Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyeong-Moon Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.870353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3738","last_page":"3755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.18809999525547028,"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/T11439","display_name":"Video Analysis and Summarization","score":0.18809999525547028,"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":0.1485999971628189,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13459999859333038,"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/feature","display_name":"Feature (linguistics)","score":0.2624000012874603},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25529998540878296},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.22380000352859497},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.22269999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5853000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24120000004768372},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2240999937057495},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22380000352859497},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22269999980926514}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.171","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2607.22729","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22729","pdf_url":"https://arxiv.org/pdf/2607.22729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.171","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Backchannels,":[0],"which":[1,41],"signal":[2],"listener":[3],"states":[4],"like":[5],"empathy":[6],"and":[7,22,33,111],"understanding,":[8],"are":[9,42],"fundamental":[10],"to":[11,86],"natural":[12],"human":[13],"interaction.":[14],"However,":[15],"current":[16],"approaches":[17],"rely":[18],"solely":[19],"on":[20],"audio":[21],"text.":[23],"This":[24],"omits":[25],"crucial":[26],"visual":[27,64],"cues,":[28],"such":[29,122],"as":[30,35,37,123],"facial":[31],"expressions":[32],"gestures,":[34],"well":[36],"broader":[38],"conversational":[39,88],"contexts,":[40],"necessary":[43],"for":[44,55,98],"accurate":[45],"prediction.":[46,100],"In":[47],"this":[48],"paper,":[49],"we":[50],"introduce":[51],"Context-Aware":[52],"Multimodal":[53,68],"Alignment":[54,69,79,92],"Backchannel":[56,91],"Prediction":[57],"(CAMA-BC),":[58],"a":[59],"novel":[60],"framework":[61],"that":[62,104],"leverages":[63],"information":[65],"through":[66],"Multi-Layer":[67],"(MMA).":[70],"Our":[71],"alignment":[72],"process":[73],"comprises":[74],"two":[75],"stages.":[76],"First,":[77],"Context":[78],"(MMA-CA)":[80],"utilizes":[81],"unlabeled":[82],"dialogues":[83],"with":[84,115],"videos":[85],"capture":[87],"contexts.":[89],"Next,":[90],"(MMA-BA)":[93],"fine-tunes":[94],"the":[95],"representations":[96],"specifically":[97],"backchannel":[99],"Experimental":[101],"results":[102],"show":[103],"CAMA-BC":[105],"significantly":[106],"outperforms":[107],"both":[108],"existing":[109],"methods":[110],"simple":[112],"multimodal":[113],"baselines,":[114],"particular":[116],"effectiveness":[117],"in":[118],"recognizing":[119],"complex":[120],"backchannels":[121],"empathy.":[124]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2026-07-02T00:00:00"}