{"id":"https://openalex.org/W7127145376","doi":"https://doi.org/10.1145/3774904.3793046","title":"StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing","display_name":"StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127145376","doi":"https://doi.org/10.1145/3774904.3793046"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2601.22738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22738","pdf_url":"https://arxiv.org/pdf/2601.22738","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.22738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124853872","display_name":"Han Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120050138","display_name":"Deyi Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Deyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074956841","display_name":"Lanyun Zhu","orcid":"https://orcid.org/0000-0001-7309-3330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Lanyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124815343","display_name":"Jiebo Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jiebo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124784432","display_name":"Roy Ka-Wei Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Roy Ka-Wei","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.3203999996185303,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.3203999996185303,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.25189998745918274,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11389999836683273,"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/encoder","display_name":"Encoder","score":0.6312000155448914},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6092000007629395},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5213000178337097},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4447000026702881},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.4059999883174896},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3970000147819519},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.38679999113082886},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373000025749207},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.38679999113082886},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C180611318","wikidata":"https://www.wikidata.org/wiki/Q7316902","display_name":"Retransmission","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2776741261","wikidata":"https://www.wikidata.org/wiki/Q3027665","display_name":"Live streaming","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C53605480","wikidata":"https://www.wikidata.org/wiki/Q852595","display_name":"Geotagging","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2601.22738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22738","pdf_url":"https://arxiv.org/pdf/2601.22738","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.22738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22738","pdf_url":"https://arxiv.org/pdf/2601.22738","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4810864329338074}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Live":[0],"streaming":[1,25,31,49,104,125,151],"platforms":[2],"require":[3],"real-time":[4],"monitoring":[5],"and":[6,13,19,57,81,110,114,136,144],"reaction":[7],"to":[8,36,54,74],"social":[9,103,152],"signals,":[10,80],"utilizing":[11],"partial":[12],"asynchronous":[14],"evidence":[15],"from":[16],"video,":[17],"text,":[18],"audio.":[20],"We":[21,98],"propose":[22],"StreamSense,":[23],"a":[24,29,37,70],"detector":[26],"that":[27,86,118,141],"couples":[28],"lightweight":[30,48],"encoder":[32,65],"with":[33,46,78],"selective":[34,142],"routing":[35],"Vision-Language":[38],"Model":[39],"(VLM)":[40],"expert.":[41],"StreamSense":[42,100,119],"handles":[43],"most":[44],"timestamps":[45],"the":[47,55,115,130],"encoder,":[50],"escalates":[51],"hard/ambiguous":[52],"cases":[53],"VLM,":[56,131],"defers":[58],"decisions":[59],"when":[60],"context":[61],"is":[62,66,155],"insufficient.":[63],"The":[64],"trained":[67],"using":[68],"(i)":[69],"cross-modal":[71],"contrastive":[72],"term":[73],"align":[75],"visual/audio":[76],"cues":[77],"textual":[79],"(ii)":[82],"an":[83],"IoU-weighted":[84],"loss":[85],"down-weights":[87],"poorly":[88],"overlapping":[89],"target":[90],"segments,":[91],"mitigating":[92],"label":[93],"interference":[94],"across":[95],"segment":[96],"boundaries.":[97],"evaluate":[99],"on":[101,158],"multiple":[102],"detection":[105],"tasks":[106],"(e.g.,":[107],"sentiment":[108],"classification":[109],"hate":[111],"content":[112],"moderation),":[113],"results":[116,139],"show":[117],"achieves":[120],"higher":[121],"accuracy":[122],"than":[123],"VLM-only":[124],"while":[126],"only":[127],"occasionally":[128],"invoking":[129],"thereby":[132],"reducing":[133],"average":[134],"latency":[135],"compute.":[137],"Our":[138],"indicate":[140],"escalation":[143],"deferral":[145],"are":[146],"effective":[147],"primitives":[148],"for":[149],"understanding":[150],"tasks.":[153],"Code":[154],"publicly":[156],"available":[157],"GitHub.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2026-02-03T00:00:00"}