{"id":"https://openalex.org/W4403713393","doi":"https://doi.org/10.1109/iccv51701.2025.02127","title":"HERMES: Temporal-Coherent Long-form Understanding with Episodes and Semantics","display_name":"HERMES: Temporal-Coherent Long-form Understanding with Episodes and Semantics","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4403713393","doi":"https://doi.org/10.1109/iccv51701.2025.02127"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02127","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/2408.17443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010143180","display_name":"Gueter Josmy Faure","orcid":"https://orcid.org/0000-0002-8721-847X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Gueter Josmy Faure","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103054554","display_name":"Jia-Fong Yeh","orcid":"https://orcid.org/0000-0002-7512-9920"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Fong Yeh","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090573773","display_name":"Min-Hung Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min-Hung Chen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034130957","display_name":"Hung-Ting Su","orcid":"https://orcid.org/0009-0007-5212-0927"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Ting Su","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073849580","display_name":"Shang\u2010Hong Lai","orcid":"https://orcid.org/0000-0002-5092-993X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Hong Lai","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043898632","display_name":"Winston H. Hsu","orcid":"https://orcid.org/0000-0002-3330-0638"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Winston H. Hsu","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"22911","last_page":"22921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8440999984741211,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8440999984741211,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7813000082969666,"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/semantics","display_name":"Semantics (computer science)","score":0.6072301864624023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4708024263381958},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3510696589946747},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29400885105133057},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.2411244809627533}],"concepts":[{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6072301864624023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4708024263381958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3510696589946747},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29400885105133057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.2411244809627533}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02127","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:2408.17443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.17443","pdf_url":"https://arxiv.org/pdf/2408.17443","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":"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":"doi:10.48550/arxiv.2408.17443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.17443","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.17443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.17443","pdf_url":"https://arxiv.org/pdf/2408.17443","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":"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2053618139"],"abstract_inverted_index":{"Long-form":[0],"video":[1],"understanding":[2,48,153],"presents":[3],"unique":[4],"challenges":[5],"that":[6,36,57,114],"extend":[7],"beyond":[8],"traditional":[9],"short-video":[10],"analysis":[11],"approaches,":[12],"particularly":[13],"in":[14,155],"capturing":[15],"long-range":[16],"dependencies,":[17],"processing":[18],"redundant":[19],"information":[20,97],"efficiently,":[21],"and":[22,51,137,158],"extracting":[23],"high-level":[24],"semantic":[25,96],"concepts.":[26],"To":[27],"address":[28],"these":[29,93,115],"challenges,":[30],"we":[31],"propose":[32],"a":[33,66,143],"novel":[34],"approach":[35],"more":[37],"accurately":[38],"reflects":[39],"human":[40],"cognition.":[41],"This":[42],"paper":[43],"introduces":[44],"HERMES:":[45],"temporal-coHERent":[46],"long-forM":[47],"with":[49,95],"Episodes":[50],"Semantics,":[52],"featuring":[53],"two":[54],"versatile":[55],"modules":[56,116],"can":[58,117],"enhance":[59],"existing":[60,122],"video-language":[61],"models":[62],"or":[63],"operate":[64],"as":[65],"standalone":[67,144],"system.":[68],"Our":[69,88],"Episodic":[70],"COmpressor":[71],"(ECO)":[72],"efficiently":[73],"aggregates":[74],"representations":[75,94],"from":[76],"micro":[77],"to":[78,135],"semi-macro":[79],"levels,":[80],"reducing":[81,104,130],"computational":[82],"overhead":[83],"while":[84,107,129],"preserving":[85,108],"temporal":[86],"dependencies.":[87],"Semantics":[89],"ReTRiever":[90],"(SeTR)":[91],"enriches":[92],"by":[98,133,140],"focusing":[99],"on":[100],"broader":[101],"context,":[102],"dramatically":[103],"feature":[105],"dimensionality":[106],"relevant":[109],"macro-level":[110],"information.":[111],"We":[112],"demonstrate":[113],"be":[118],"seamlessly":[119],"integrated":[120],"into":[121],"SOTA":[123],"models,":[124],"consistently":[125],"improving":[126],"their":[127],"performance":[128,149],"inference":[131],"latency":[132],"up":[134],"43%":[136],"memory":[138],"usage":[139],"46%.":[141],"As":[142],"system,":[145],"HERMES":[146],"achieves":[147],"state-of-the-art":[148],"across":[150],"multiple":[151],"long-video":[152],"benchmarks":[154],"both":[156],"zero-shot":[157],"fully-supervised":[159],"settings.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}