{"id":"https://openalex.org/W4414760229","doi":"https://doi.org/10.1109/iccv51701.2025.00975","title":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","display_name":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414760229","doi":"https://doi.org/10.1109/iccv51701.2025.00975"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.04758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kaname Yokoyama","orcid":null},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaname Yokoyama","raw_affiliation_strings":["Toyota Technological Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042267985","display_name":"Chihiro Nakatani","orcid":"https://orcid.org/0009-0000-5966-2672"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chihiro Nakatani","raw_affiliation_strings":["Toyota Technological Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053167635","display_name":"Norimichi Ukita","orcid":"https://orcid.org/0000-0002-0240-1065"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norimichi Ukita","raw_affiliation_strings":["Toyota Technological Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute","institution_ids":["https://openalex.org/I4840577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4840577"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10475","last_page":"10484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9368000030517578,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9368000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5902000069618225},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5508999824523926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3935999870300293},{"id":"https://openalex.org/keywords/global-optimization","display_name":"Global optimization","score":0.32339999079704285}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555400013923645},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29170000553131104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.04758","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04758","pdf_url":"https://arxiv.org/pdf/2509.04758","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"},{"id":"doi:10.48550/arxiv.2509.04758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04758","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.04758","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04758","pdf_url":"https://arxiv.org/pdf/2509.04758","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"dynamic":[3],"human":[4],"group":[5,50,59,114],"detection":[6,51,115],"in":[7,38,52,79],"videos.":[8],"For":[9,55],"detecting":[10],"complex":[11],"groups,":[12],"not":[13,77],"only":[14],"the":[15,24,28,58,72],"local":[16,33],"appearance":[17,36],"features":[18,37],"of":[19,27],"in-group":[20],"members":[21],"but":[22],"also":[23],"global":[25,35,89],"context":[26],"scene":[29],"are":[30,41,69,76],"important.":[31],"Such":[32],"and":[34],"each":[39],"frame":[40],"extracted":[42],"using":[43,91],"a":[44,80,92],"Vision-Language":[45],"Model":[46],"(VLM)":[47],"augmented":[48],"for":[49],"our":[53,82,101,110],"method.":[54],"further":[56],"improvement,":[57],"structure":[60],"should":[61],"be":[62],"consistent":[63],"over":[64],"time.":[65],"While":[66],"previous":[67],"methods":[68,116],"stabilized":[70],"on":[71,117],"assumption":[73],"that":[74,109],"groups":[75,87],"changed":[78],"video,":[81],"method":[83,111],"detects":[84],"dynamically":[85],"changing":[86],"by":[88,100],"optimization":[90],"graph":[93],"with":[94],"all":[95],"frames'":[96],"groupness":[97],"probabilities":[98],"estimated":[99],"groupness-augmented":[102],"CLIP":[103],"features.":[104],"Our":[105],"experimental":[106],"results":[107],"demonstrate":[108],"outperforms":[112],"state-of-the-art":[113],"public":[118],"datasets.":[119],"Code:":[120],"https://github.com/irajisamurai/VLM-GroupDetection.git":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}