{"id":"https://openalex.org/W4414742217","doi":"https://doi.org/10.1145/3772356.3772390","title":"Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI","display_name":"Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4414742217","doi":"https://doi.org/10.1145/3772356.3772390"},"language":"en","primary_location":{"id":"doi:10.1145/3772356.3772390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772390","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057448142","display_name":"Jiangkai Wu","orcid":"https://orcid.org/0009-0007-7628-6673"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangkai Wu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7628-6673","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Ren","orcid":"https://orcid.org/0009-0004-4133-7416"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Ren","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4133-7416","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liming Liu","orcid":"https://orcid.org/0009-0004-9168-4897"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-9168-4897","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058634226","display_name":"Xinggong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinggong Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0484-5951","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057448142"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24684625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"402","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.82669997215271,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.82669997215271,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6327000260353088},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5443000197410583},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.41499999165534973},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3953999876976013},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805400013923645},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5443000197410583},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C540522513","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videotelephony","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2779333187","wikidata":"https://www.wikidata.org/wiki/Q3132648","display_name":"Quality of experience","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3772356.3772390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772390","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.10510","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10510","pdf_url":"https://arxiv.org/pdf/2507.10510","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.10510","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10510","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3772356.3772390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772390","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6263369104","display_name":null,"funder_award_id":"62431017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4414742217.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2849781392","https://openalex.org/W2540285146","https://openalex.org/W2397506972","https://openalex.org/W4402727512","https://openalex.org/W4401176519","https://openalex.org/W2167407752","https://openalex.org/W2150453038","https://openalex.org/W4283204765","https://openalex.org/W4376130027","https://openalex.org/W2744628735","https://openalex.org/W2172073677","https://openalex.org/W2523901075","https://openalex.org/W4413146426","https://openalex.org/W4415537505","https://openalex.org/W4393245623"],"related_works":[],"abstract_inverted_index":{"AI":[0,32,79,116,201],"Video":[1,117,149,187,202],"Chat":[2,118],"emerges":[3],"as":[4,35],"a":[5,17,20,40,75,83,132],"new":[6],"paradigm":[7],"for":[8,65,91,135,159,200],"Real-time":[9],"Communication":[10],"(RTC),":[11],"where":[12],"one":[13],"peer":[14],"is":[15,131,205],"not":[16],"human,":[18],"but":[19],"Multimodal":[21],"Large":[22],"Language":[23],"Model":[24],"(MLLM).":[25],"This":[26],"makes":[27],"interaction":[28],"between":[29,115],"humans":[30],"and":[31,119,161,197],"more":[33],"intuitive,":[34],"if":[36],"chatting":[37],"face-to-face":[38],"with":[39],"real":[41,84],"person.":[42,85],"However,":[43],"this":[44],"poses":[45],"significant":[46],"challenges":[47],"to":[48,69,104,166],"latency,":[49],"because":[50],"the":[51,58,96,112,153,171,182],"MLLM":[52,144,178],"inference":[53],"takes":[54],"up":[55],"most":[56],"of":[57,155,173],"response":[59],"time,":[60],"leaving":[61],"very":[62],"little":[63],"time":[64],"video":[66,157,174],"streaming.":[67],"Due":[68],"network":[70,97],"uncertainty,":[71],"transmission":[72],"latency":[73],"becomes":[74],"critical":[76],"bottleneck":[77],"preventing":[78],"from":[80,100],"being":[81],"like":[82],"To":[86,138,169],"address":[87],"this,":[88],"we":[89,126,146,180,192],"call":[90],"AI-oriented":[92],"RTC":[93],"research,":[94],"exploring":[95],"requirement":[98],"shift":[99],"\"humans":[101],"watching":[102],"video\"":[103],"\"AI":[105],"understanding":[106],"video\".":[107],"We":[108],"begin":[109],"by":[110],"recognizing":[111],"main":[113],"differences":[114],"traditional":[120],"RTC.":[121],"Then,":[122],"through":[123],"prototype":[124],"measurements,":[125],"identify":[127],"that":[128,151],"ultra-low":[129],"bitrate":[130,140,163],"key":[133],"factor":[134],"low":[136],"latency.":[137],"reduce":[139],"dramatically":[141],"while":[142],"maintaining":[143],"accuracy,":[145,179],"propose":[147],"Context-Aware":[148],"Streaming":[150],"recognizes":[152],"importance":[154],"each":[156],"region":[158],"chat":[160],"allocates":[162],"almost":[164],"exclusively":[165],"chat-important":[167],"regions.":[168],"evaluate":[170],"impact":[172],"streaming":[175],"quality":[176],"on":[177],"build":[181],"first":[183],"benchmark,":[184],"named":[185],"Degraded":[186],"Understanding":[188],"Benchmark":[189],"(DeViBench).":[190],"Finally,":[191],"discuss":[193],"some":[194],"open":[195],"questions":[196],"ongoing":[198],"solutions":[199],"Chat.":[203],"DeViBench":[204],"open-sourced":[206],"at:":[207],"https://github.com/pku-netvideo/DeViBench.":[208]},"counts_by_year":[],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2025-10-02T00:00:00"}
