{"id":"https://openalex.org/W4416403908","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00027","title":"Few-Shot Action Scene Graph Generation from Video via Multimodal Language Models for Structuring Spatial Experience","display_name":"Few-Shot Action Scene Graph Generation from Video via Multimodal Language Models for Structuring Spatial Experience","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4416403908","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00027"},"language":null,"primary_location":{"id":"doi:10.1109/ismar-adjunct68609.2025.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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/A5112877383","display_name":"Jin-Seok Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinseok Hong","raw_affiliation_strings":["KAIST UVR Lab"],"affiliations":[{"raw_affiliation_string":"KAIST UVR Lab","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006771820","display_name":"Hyerim Park","orcid":"https://orcid.org/0000-0001-6764-4490"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyerim Park","raw_affiliation_strings":["KAIST PMRC"],"affiliations":[{"raw_affiliation_string":"KAIST PMRC","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109535854","display_name":"Heejeong Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heejeong Ko","raw_affiliation_strings":["KAIST UVR Lab"],"affiliations":[{"raw_affiliation_string":"KAIST UVR Lab","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023177829","display_name":"Woontack Woo","orcid":"https://orcid.org/0000-0002-5501-4421"},"institutions":[{"id":"https://openalex.org/I4210132911","display_name":"Universidad Villa Rica","ror":"https://ror.org/048yh2980","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210132911"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Woontack Woo","raw_affiliation_strings":["UVR Lab,KAIST KI-ITC ARRC"],"affiliations":[{"raw_affiliation_string":"UVR Lab,KAIST KI-ITC ARRC","institution_ids":["https://openalex.org/I4210132911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112877383"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38484707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9878000020980835,"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":0.9878000020980835,"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/T12290","display_name":"Human Motion and Animation","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0017000000225380063,"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/structuring","display_name":"Structuring","score":0.7766000032424927},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7214000225067139},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4607999920845032},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39079999923706055},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3555999994277954},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808899998664856},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.7766000032424927},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7214000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626999735832214},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismar-adjunct68609.2025.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2888101838","https://openalex.org/W2902539442","https://openalex.org/W2960202457","https://openalex.org/W3034548564","https://openalex.org/W3035154952","https://openalex.org/W4200498145","https://openalex.org/W4214755412","https://openalex.org/W4282981352","https://openalex.org/W4286611064","https://openalex.org/W4290188436","https://openalex.org/W4312322722","https://openalex.org/W4385570088","https://openalex.org/W4387917672","https://openalex.org/W4391324012","https://openalex.org/W4394625734","https://openalex.org/W4394811248","https://openalex.org/W4400229577","https://openalex.org/W4402703022","https://openalex.org/W4402727090","https://openalex.org/W4402754270","https://openalex.org/W4403760883","https://openalex.org/W4404916475","https://openalex.org/W4404965864","https://openalex.org/W4406266242","https://openalex.org/W4408323594","https://openalex.org/W4408358257","https://openalex.org/W4408658474","https://openalex.org/W4411544860","https://openalex.org/W4413145624","https://openalex.org/W4413553594"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,35,52,91],"multimodal":[3,32],"framework":[4,69],"that":[5],"uses":[6],"few-shot":[7,59],"language":[8,54],"models":[9],"to":[10],"generate":[11],"action":[12,30],"scene":[13,46],"graphs":[14],"from":[15,49],"raw":[16],"video":[17],"for":[18],"structuring":[19],"spatial":[20,77],"experiences":[21,78],"in":[22],"extended":[23],"reality":[24],"(XR).":[25],"The":[26,86],"system":[27],"integrates":[28],"unsupervised":[29],"segmentation,":[31],"captioning":[33],"with":[34],"vision-language":[36],"model":[37,55,84],"(VLM)":[38],"guided":[39],"by":[40],"speech":[41],"and":[42,45,65,73,102],"motion":[43,66],"cues,":[44],"graph":[47],"generation":[48],"captions":[50],"using":[51],"large":[53],"(LLM),":[56],"both":[57],"leveraging":[58],"prompting.":[60],"By":[61],"combining":[62],"visual,":[63],"verbal,":[64],"inputs,":[67],"the":[68],"produces":[70],"semantically":[71],"rich":[72],"accurate":[74],"representations":[75],"of":[76,93],"without":[79],"requiring":[80],"annotated":[81],"data":[82],"or":[83],"fine-tuning.":[85],"resulting":[87],"outputs":[88],"will":[89],"support":[90],"range":[92],"downstream":[94],"XR":[95],"applications,":[96],"including":[97],"adaptive":[98],"playback,":[99],"intent-driven":[100],"retrieval,":[101],"flexible":[103],"content":[104],"reconstruction.":[105]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-18T00:00:00"}