{"id":"https://openalex.org/W4415708210","doi":"https://doi.org/10.1109/icme59968.2025.11209399","title":"SKL-CLIP: Learning Skeleton-Based Action Representations via Language Supervision","display_name":"SKL-CLIP: Learning Skeleton-Based Action Representations via Language Supervision","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708210","doi":"https://doi.org/10.1109/icme59968.2025.11209399"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5042411401","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-6735-7667"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Southeast University,Nanjing,China,210000"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210000","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108825895","display_name":"Jiuxin Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["Southeast University,Nanjing,China,210000"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210000","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018527272","display_name":"Jiawei Ge","orcid":"https://orcid.org/0000-0001-7268-7815"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Ge","raw_affiliation_strings":["Southeast University,Nanjing,China,210000"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210000","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353385","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-5365-8787"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Southeast University,Nanjing,China,210000"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210000","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100461575","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-5209-9063"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Southeast University,Nanjing,China,210000"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210000","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042411401"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31019388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5415999889373779,"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":0.5415999889373779,"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":0.2371000051498413,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10840000212192535,"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/leverage","display_name":"Leverage (statistics)","score":0.7077000141143799},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6949999928474426},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5644999742507935},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5271000266075134},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3375999927520752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077000141143799},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7077000141143799},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6949999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6949999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5648999810218811},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.2565999925136566},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2400717490","https://openalex.org/W2603705233","https://openalex.org/W2963076818","https://openalex.org/W2963283377","https://openalex.org/W2963369114","https://openalex.org/W2964134613","https://openalex.org/W2972073579","https://openalex.org/W2987427063","https://openalex.org/W3006198072","https://openalex.org/W3033793613","https://openalex.org/W3035050855","https://openalex.org/W3109093849","https://openalex.org/W3169413442","https://openalex.org/W3195429019","https://openalex.org/W3203227473","https://openalex.org/W3203711169","https://openalex.org/W4200634815","https://openalex.org/W4283396563","https://openalex.org/W4312480274","https://openalex.org/W4386065554","https://openalex.org/W4386072441","https://openalex.org/W4387969459","https://openalex.org/W4388004144","https://openalex.org/W4390871852","https://openalex.org/W4400618545","https://openalex.org/W4403791161"],"related_works":[],"abstract_inverted_index":{"CLIP,":[0],"widely":[1],"used":[2],"in":[3],"multimodal":[4],"learning,":[5,63],"excels":[6],"due":[7,24],"to":[8,17,25,56,74,79,86],"its":[9],"large-scale":[10],"image-text":[11],"pretraining.":[12],"However,":[13],"applying":[14],"CLIP-like":[15],"architectures":[16],"skeleton-based":[18,108],"action":[19,109],"representation":[20,62],"learning":[21],"presents":[22],"challenges":[23],"the":[26,32,67],"incompatible":[27],"non-visual":[28],"data":[29],"structure":[30],"and":[31,59,82,93,100,120],"limited":[33],"scale":[34],"of":[35,70],"skeleton":[36],"datasets,":[37,90],"which":[38],"hinder":[39],"robust":[40],"generalization.":[41],"To":[42],"address":[43],"these":[44],"issues,":[45],"we":[46],"propose":[47],"SKL-CLIP,":[48],"a":[49],"framework":[50],"that":[51,104],"incorporates":[52],"Supervised":[53],"Self-Contrastive":[54],"Learning":[55],"mitigate":[57],"overfitting":[58],"enhance":[60],"transferable":[61],"Knowledge":[64],"Distillation":[65],"from":[66],"textual":[68],"encoder":[69],"pretrained":[71],"CLIP":[72],"models":[73],"preserve":[75],"generalization":[76],"while":[77],"adapting":[78],"skeleton-text":[80],"scenarios,":[81],"Multi-Domain":[83],"Parallel":[84],"Training":[85],"leverage":[87],"diverse":[88],"support":[89],"improving":[91],"cross-dataset":[92],"zero-shot":[94,121],"recognition.":[95],"Extensive":[96],"experiments":[97],"on":[98],"NTU":[99],"PKU":[101],"datasets":[102],"demonstrate":[103],"SKL-CLIP":[105],"significantly":[106],"advances":[107],"representation,":[110],"achieving":[111],"state-of-the-art":[112],"performance":[113],"across":[114],"fully-supervised,":[115],"cross-data":[116],"unsupervised":[117],"domain":[118],"adaptation,":[119],"tasks.":[122]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}