{"id":"https://openalex.org/W4417302301","doi":"https://doi.org/10.1109/iccv51701.2025.01847","title":"HiERO: Understanding the Hierarchy of Human Behavior Enhances Reasoning on Egocentric Videos","display_name":"HiERO: Understanding the Hierarchy of Human Behavior Enhances Reasoning on Egocentric Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417302301","doi":"https://doi.org/10.1109/iccv51701.2025.01847"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01847","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.12911","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045918600","display_name":"Simone Peirone","orcid":"https://orcid.org/0009-0007-3204-3207"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Alberto Peirone","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016675020","display_name":"Francesca Pistilli","orcid":"https://orcid.org/0000-0001-9372-032X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Pistilli","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050576327","display_name":"Giuseppe Averta","orcid":"https://orcid.org/0000-0003-1212-3465"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Averta","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3585878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19862","last_page":"19871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4844000041484833,"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":0.4844000041484833,"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":0.3571000099182129,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02710000053048134,"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/hierarchy","display_name":"Hierarchy","score":0.8501999974250793},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.722100019454956},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6561999917030334},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3483000099658966},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2994000017642975}],"concepts":[{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.8501999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646999955177307},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.722100019454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.682699978351593},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6561999917030334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01847","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:2505.12911","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12911","pdf_url":"https://arxiv.org/pdf/2505.12911","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.12911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12911","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.12911","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12911","pdf_url":"https://arxiv.org/pdf/2505.12911","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/G4508289328","display_name":null,"funder_award_id":"PE00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7248538987","display_name":null,"funder_award_id":"1555 11/10/2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417302301.pdf","grobid_xml":"https://content.openalex.org/works/W4417302301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"activities":[1,171],"are":[2],"particularly":[3],"complex":[4],"and":[5,7,53,92,118,126,138],"variable,":[6],"this":[8],"makes":[9],"challenging":[10],"for":[11,121,139,172],"deep":[12],"learning":[13,123,141],"models":[14],"to":[15,57,69],"reason":[16,59],"about":[17,60],"them.":[18],"However,":[19],"we":[20],"note":[21],"that":[22,41],"such":[23,42],"variability":[24],"does":[25],"have":[26],"an":[27,96],"underlying":[28],"structure,":[29],"composed":[30],"of":[31,34,36,50,103,163,166,169],"a":[32,66,148],"hierarchy":[33,168],"patterns":[35],"related":[37],"actions.":[38],"We":[39,63,99],"argue":[40],"structure":[43],"can":[44,54],"emerge":[45],"naturally":[46],"from":[47],"unscripted":[48],"videos":[49],"human":[51,170],"activities,":[52],"be":[55],"leveraged":[56],"better":[58],"their":[61,85],"content.":[62],"present":[64],"HiERO,":[65],"weakly-supervised":[67],"method":[68],"enrich":[70],"video":[71,82],"segments":[72],"features":[73,106],"with":[74,84,95,107,114],"the":[75,101,136,161,167],"corresponding":[76],"hierarchical":[77,97],"activity":[78],"threads.":[79],"By":[80],"aligning":[81],"clips":[83],"narrated":[86],"descriptions,":[87],"HiERO":[88,130],"infers":[89],"contextual,":[90],"semantic":[91],"temporal":[93],"reasoning":[94,174],"architecture.":[98],"prove":[100,160],"potential":[102],"our":[104],"enriched":[105],"multiple":[108,173],"video-text":[109],"alignment":[110],"benchmarks":[111],"(EgoMCQ,":[112],"EgoNLQ)":[113],"minimal":[115],"additional":[116],"training,":[117],"in":[119,134,155,176],"zero-shot":[120],"procedure":[122,140],"tasks":[124,142,175],"(EgoProceL":[125],"Ego4D":[127],"Goal-Step).":[128],"Notably,":[129],"achieves":[131],"state-of-the-art":[132],"performance":[133],"all":[135],"benchmarks,":[137],"it":[143],"outperforms":[144],"fully-supervised":[145],"methods":[146],"by":[147],"large":[149],"margin":[150],"(+12.5%":[151],"F1":[152],"on":[153],"EgoProceL)":[154],"zero":[156],"shot.":[157],"Our":[158],"results":[159],"relevance":[162],"using":[164],"knowledge":[165],"egocentric":[177],"vision.":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}