{"id":"https://openalex.org/W4411635485","doi":"https://doi.org/10.1145/3731715.3733303","title":"Demonstration Meets Typed Events: Type Specific Video Semantic Role Labeling via Multimodal Prompting and Retrieval","display_name":"Demonstration Meets Typed Events: Type Specific Video Semantic Role Labeling via Multimodal Prompting and Retrieval","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635485","doi":"https://doi.org/10.1145/3731715.3733303"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5070266378","display_name":"Haonan Wei","orcid":"https://orcid.org/0009-0006-7772-7840"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanxiao Wei","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432128","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0002-7112-126X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023216803","display_name":"Chunjia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjia Wang","raw_affiliation_strings":["China Unicom, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055900704","display_name":"Guangyao Su","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyao Su","raw_affiliation_strings":["China Unicom Software Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Software Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111703263","display_name":"Tao Zhou","orcid":"https://orcid.org/0009-0001-6792-2072"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhou","raw_affiliation_strings":["China Unicom Software Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Software Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070266378"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12932952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1461","last_page":"1469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8071010112762451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48431792855262756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4359997808933258},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4090937674045563},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3608129620552063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071010112762451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48431792855262756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359997808933258},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4090937674045563},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3608129620552063}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2507397568","https://openalex.org/W2597601064","https://openalex.org/W2747329762","https://openalex.org/W3181951703","https://openalex.org/W4225414521","https://openalex.org/W4229005866","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312738368","https://openalex.org/W4320235125","https://openalex.org/W4321614506","https://openalex.org/W4376607849","https://openalex.org/W4382469217","https://openalex.org/W4385567149","https://openalex.org/W4387969604","https://openalex.org/W4389520006","https://openalex.org/W4401043163","https://openalex.org/W4401043558","https://openalex.org/W4401203039","https://openalex.org/W4404003037","https://openalex.org/W4404781913","https://openalex.org/W4404782964","https://openalex.org/W4405035922"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Video":[0,62],"Semantic":[1,63],"Role":[2,64],"Labeling":[3,65],"(VidSRL)":[4],"aims":[5],"to":[6,31,97,130],"detect":[7],"salient":[8],"events":[9],"and":[10,39,110,128,136,143,154],"label":[11],"their":[12],"semantic":[13,40],"roles":[14,29,38],"from":[15],"videos.":[16],"Existing":[17],"methods":[18],"often":[19],"struggle":[20],"with":[21,66,125],"missing,":[22],"redundant,":[23],"misordered,":[24],"or":[25],"incorrectly":[26],"understood":[27],"argument":[28,37,99,144],"due":[30],"ignoring":[32],"the":[33,36,46,114,123,133,139,156],"semantics":[34,134],"of":[35,49,135],"structure":[41],"within":[42],"events.":[43],"Inspired":[44],"by":[45,55],"labeling":[47],"logic":[48],"human":[50],"annotators,":[51],"we":[52],"address":[53],"this":[54],"presenting":[56],"a":[57,76,87,93],"novel":[58],"method,":[59],"Type":[60],"Specific":[61],"Demonstration-Enhanced":[67],"Vision-Language":[68],"Model":[69],"(TypesDeV).":[70],"Our":[71,146],"method":[72],"is":[73],"based":[74],"on":[75,151,162],"three-stage":[77],"framework:":[78],"(1)":[79],"Selection":[80],"involves":[81],"predicting":[82],"potential":[83],"event":[84,108],"types":[85],"using":[86,166],"video":[88],"classifier,":[89],"(2)":[90],"Generation":[91],"uses":[92],"vision-language":[94],"model":[95],"(VLM)":[96],"generate":[98],"role":[100,103],"descriptions":[101,117],"(semantic":[102],"labels)":[104],"for":[105,155],"each":[106],"candidate":[107],"type,":[109],"(3)":[111],"Retrieval":[112],"selects":[113],"best":[115],"matching":[116],"through":[118],"video-to-text":[119],"retrieval.":[120],"We":[121],"enhance":[122],"VLM":[124],"event-type-specific":[126],"prompts":[127],"demonstrations":[129],"explicitly":[131],"capture":[132],"relationships":[137],"between":[138],"verb":[140],"(event":[141],"type)":[142],"roles.":[145],"approach":[147],"achieves":[148,159],"new":[149],"state-of-the-art":[150],"multiple":[152],"metrics,":[153],"first":[157],"time":[158],"human-level":[160],"performance":[161],"most":[163],"metrics":[164],"when":[165],"ground-truth":[167],"verbs.":[168]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}