{"id":"https://openalex.org/W7124423201","doi":"https://doi.org/10.48550/arxiv.2601.10592","title":"Action100M: A Large-scale Video Action Dataset","display_name":"Action100M: A Large-scale Video Action Dataset","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124423201","doi":"https://doi.org/10.48550/arxiv.2601.10592"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.10592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10592","pdf_url":"https://arxiv.org/pdf/2601.10592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.10592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020620488","display_name":"Delong Chen","orcid":"https://orcid.org/0000-0002-8172-2894","observed_orcids":["https://orcid.org/0000-0002-8172-2894"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Delong","raw_affiliation_strings":["HKUST ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST ,","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063524006","display_name":"Tejaswi Kasarla","orcid":"https://orcid.org/0000-0003-4580-9383","observed_orcids":["https://orcid.org/0000-0003-4580-9383"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kasarla, Tejaswi","raw_affiliation_strings":["University of Amsterdam ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam ,","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113851214","display_name":"Yejin Bang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bang, Yejin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111151249","display_name":"Mustafa Shukor","orcid":"https://orcid.org/0000-0002-3100-6689","observed_orcids":["https://orcid.org/0000-0002-3100-6689"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shukor, Mustafa","raw_affiliation_strings":["Sorbonne Universit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066145828","display_name":"Willy Chung","orcid":"https://orcid.org/0000-0003-4499-525X","observed_orcids":["https://orcid.org/0000-0003-4499-525X"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chung, Willy","raw_affiliation_strings":["Sorbonne Universit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113230473","display_name":"Jade Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jade","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119946713","display_name":"Allen Bolourchi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bolourchi, Allen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015776030","display_name":"Th\u00e9o Moutakanni","orcid":"https://orcid.org/0009-0000-2681-5169","observed_orcids":["https://orcid.org/0009-0000-2681-5169"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moutakanni, Theo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132","observed_orcids":["https://orcid.org/0000-0002-0628-7132"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fung, Pascale","raw_affiliation_strings":["HKUST ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST ,","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9491999745368958,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9491999745368958,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04729999974370003,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/video-action-recognition","display_name":"video action recognition","score":0.6970000267028809},{"id":"https://openalex.org/keywords/educational-videos","display_name":"educational videos","score":0.8299999833106995},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.6290000081062317},{"id":"https://openalex.org/keywords/self-refinement","display_name":"self-refinement","score":0.6190000176429749},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.5180000066757202},{"id":"https://openalex.org/keywords/zero-shot-action-recognition","display_name":"zero-shot action recognition","score":0.6110000014305115},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.6610000133514404},{"id":"https://openalex.org/keywords/world-modeling","display_name":"world modeling","score":0.75}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270000219345093},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C2779789524","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Internet video","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C2779789524","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Internet video","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2500999867916107},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2601.10592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10592","pdf_url":"https://arxiv.org/pdf/2601.10592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05660896v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-05660896v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Vision and Pattern Recognition (CVPR) EgoVis Workshop, 2026","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2601.10592","doi":"https://doi.org/10.48550/arxiv.2601.10592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.10592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.10592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10592","pdf_url":"https://arxiv.org/pdf/2601.10592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124423201.pdf","grobid_xml":"https://content.openalex.org/works/W7124423201.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2099614498","https://openalex.org/W2109698606","https://openalex.org/W2619947201","https://openalex.org/W4296406182","https://openalex.org/W4399061442","https://openalex.org/W4399657827","https://openalex.org/W4399758271","https://openalex.org/W4400341198","https://openalex.org/W4400601172","https://openalex.org/W4403370734","https://openalex.org/W4403885521","https://openalex.org/W4404407560","https://openalex.org/W4406191642","https://openalex.org/W4407815020","https://openalex.org/W4409046497","https://openalex.org/W4414693706","https://openalex.org/W4415058764","https://openalex.org/W4415109258","https://openalex.org/W4415330695","https://openalex.org/W4416035939","https://openalex.org/W4416119086","https://openalex.org/W4416131829","https://openalex.org/W4416539380","https://openalex.org/W4417091809","https://openalex.org/W4417261359","https://openalex.org/W4417297110","https://openalex.org/W6910516217","https://openalex.org/W7075994024","https://openalex.org/W7118009763"],"related_works":["https://openalex.org/W7160321522","https://openalex.org/W2120601899","https://openalex.org/W3086329735","https://openalex.org/W6979322840","https://openalex.org/W2941712317","https://openalex.org/W4408859120","https://openalex.org/W4408323594","https://openalex.org/W2897426518","https://openalex.org/W3092746951","https://openalex.org/W4221012172"],"abstract_inverted_index":{"Inferring":[0],"physical":[1,16],"actions":[2],"from":[3,37],"visual":[4],"observations":[5],"is":[6,60],"a":[7,33,63,86,93,98,131],"fundamental":[8],"capability":[9],"for":[10,134],"advancing":[11],"machine":[12],"intelligence":[13],"in":[14,137],"the":[15],"world.":[17],"Achieving":[18],"this":[19],"requires":[20],"large-scale,":[21],"open-vocabulary":[22,53],"video":[23,138],"action":[24,54,125],"datasets":[25],"that":[26,67],"span":[27],"broad":[28],"domains.":[29],"We":[30],"introduce":[31],"Action100M,":[32],"large-scale":[34],"dataset":[35],"constructed":[36],"1.2M":[38],"Internet":[39],"instructional":[40],"videos":[41],"(14.6":[42],"years":[43],"of":[44],"duration),":[45],"yielding":[46],"O(100":[47],"million)":[48],"temporally":[49],"localized":[50],"segments":[51],"with":[52,92],"supervision":[55],"and":[56,81,88,119,140],"rich":[57],"captions.":[58],"Action100M":[59,114,129],"generated":[61],"by":[62],"fully":[64],"automated":[65],"pipeline":[66],"(i)":[68],"performs":[69],"hierarchical":[70],"temporal":[71],"segmentation":[72],"using":[73],"V-JEPA":[74],"2":[75],"embeddings,":[76],"(ii)":[77],"produces":[78],"multi-level":[79],"frame":[80],"segment":[82],"captions":[83],"organized":[84],"as":[85,130],"Tree-of-Captions,":[87],"(iii)":[89],"aggregates":[90],"evidence":[91],"reasoning":[94],"model":[95],"(GPT-OSS-120B)":[96],"under":[97],"multi-round":[99],"Self-Refine":[100],"procedure":[101],"to":[102],"output":[103],"structured":[104],"annotations":[105],"(brief/detailed":[106],"action,":[107],"actor,":[108],"brief/detailed":[109],"caption).":[110],"Training":[111],"VL-JEPA":[112],"on":[113],"demonstrates":[115],"consistent":[116],"data-scaling":[117],"improvements":[118],"strong":[120],"zero-shot":[121],"performance":[122],"across":[123],"diverse":[124],"recognition":[126],"benchmarks,":[127],"establishing":[128],"new":[132],"foundation":[133],"scalable":[135],"research":[136],"understanding":[139],"world":[141],"modeling.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":17}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-17T00:00:00"}