{"id":"https://openalex.org/W4414360102","doi":"https://doi.org/10.24963/ijcai.2025/115","title":"Reliable and Diverse Hierarchical Adapter for Zero-shot Video Classification","display_name":"Reliable and Diverse Hierarchical Adapter for Zero-shot Video Classification","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360102","doi":"https://doi.org/10.24963/ijcai.2025/115"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/115","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037778075","display_name":"Wenxuan Ge","orcid":"https://orcid.org/0000-0002-4186-8944"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Ge","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029702480","display_name":"Peng Huang","orcid":"https://orcid.org/0009-0003-4102-6506"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398852","display_name":"Hongyu Qu","orcid":"https://orcid.org/0000-0002-7631-8774"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Qu","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084688255","display_name":"Guo-Sen Xie","orcid":"https://orcid.org/0000-0002-5487-9845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guosen Xie","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"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":"1026","last_page":"1034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9977999925613403,"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":0.9977999925613403,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.992900013923645,"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/adapter","display_name":"Adapter (computing)","score":0.8483999967575073},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7408000230789185},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4855000078678131},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.367000013589859},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3431999981403351},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2874999940395355},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.28619998693466187}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8483999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828000009059906},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7408000230789185},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3125},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/115","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Adapting":[0],"pre-trained":[1],"vision-language":[2],"models":[3],"to":[4,25,31,78,96,105,108,147,162],"downstream":[5,33],"tasks":[6,34],"has":[7],"emerged":[8],"as":[9,22],"a":[10,49,58,117],"novel":[11],"paradigm":[12],"for":[13,54,84,123],"zero-shot":[14,85,124],"learning.":[15],"Existing":[16],"test-time":[17],"adaptation":[18],"(TTA)":[19],"methods":[20],"such":[21],"TPT":[23],"attempt":[24],"fine-tune":[26],"visual":[27,52],"or":[28],"textual":[29],"representations":[30],"accommodate":[32],"but":[35],"still":[36],"require":[37],"expensive":[38],"optimization":[39],"costs.":[40],"To":[41],"this":[42,75,113],"end,":[43],"Training-free":[44],"Dynamic":[45],"Adapter":[46,122],"(TDA)":[47],"maintains":[48],"cache":[50,102,172],"containing":[51],"features":[53],"each":[55,138],"category":[56],"in":[57],"parameter-free":[59],"manner":[60],"and":[61,98,119,133,157],"measures":[62],"sample":[63,140],"confidence":[64],"based":[65,153,175],"on":[66,154,176,182],"prediction":[67,155],"entropy":[68,156],"of":[69,129,166,179,191],"test":[70],"samples.":[71],"Inspired":[72],"by":[73],"TDA,":[74],"work":[76],"aims":[77],"develop":[79],"the":[80,89,100,109,142,163,167,171,177,189],"first":[81],"training-free":[82],"adapter":[83],"video":[86,94,101,110,125,139,185],"classification.":[87],"Capturing":[88],"intrinsic":[90],"temporal":[91,158],"relationships":[92],"within":[93],"data":[95],"construct":[97],"maintain":[99],"is":[103,196],"key":[104],"extending":[106],"TDA":[107],"domain.":[111],"In":[112],"work,":[114],"we":[115,169],"propose":[116],"reliable":[118],"diverse":[120],"Hierarchical":[121,192],"classification,":[126],"which":[127],"consists":[128],"Frame-level":[130],"Cache":[131,135],"Refiner":[132],"Video-level":[134],"Updater.":[136],"Before":[137],"enters":[141],"corresponding":[143],"cache,":[144,168],"it":[145],"needs":[146],"be":[148],"refined":[149],"at":[150,198],"frame":[151],"level":[152],"probability":[159],"difference.":[160],"Due":[161],"limited":[164],"capacity":[165],"update":[170],"during":[173],"inference":[174],"principle":[178],"diversity.":[180],"Experiments":[181],"four":[183],"popular":[184],"classification":[186],"benchmarks":[187],"demonstrate":[188],"effectiveness":[190],"Adapter.":[193],"The":[194],"code":[195],"available":[197],"https://github.com/Gwxer/Hierarchical-Adapter.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}