{"id":"https://openalex.org/W4408235895","doi":"https://doi.org/10.1109/robio64047.2024.10907305","title":"Temporal Text Prompts for Skeleton-based Action Recognition","display_name":"Temporal Text Prompts for Skeleton-based Action Recognition","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4408235895","doi":"https://doi.org/10.1109/robio64047.2024.10907305"},"language":"en","primary_location":{"id":"doi:10.1109/robio64047.2024.10907305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5000790266","display_name":"Liyuan Liu","orcid":"https://orcid.org/0009-0006-0903-1438"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyuan Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768911","display_name":"Shaojie Zhang","orcid":"https://orcid.org/0000-0002-6780-8915"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojie Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008886406","display_name":"Yonghao Dang","orcid":"https://orcid.org/0000-0002-1118-5587"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Dang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693550","display_name":"Xubo Zhang","orcid":"https://orcid.org/0000-0002-2912-2998"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xubo Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606496","display_name":"Jianqin Yin","orcid":"https://orcid.org/0000-0002-1595-2499"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqin Yin","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"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":"1012","last_page":"1017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9614999890327454,"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":0.942799985408783,"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/computer-science","display_name":"Computer science","score":0.7158404588699341},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.6955475211143494},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5768639445304871},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5200828909873962},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5041273832321167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4660191535949707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35566475987434387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.336169958114624},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32816389203071594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11765941977500916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158404588699341},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.6955475211143494},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5768639445304871},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5200828909873962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5041273832321167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660191535949707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35566475987434387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.336169958114624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32816389203071594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11765941977500916},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio64047.2024.10907305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3764645290","display_name":null,"funder_award_id":"62173045,62273054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5631926649","display_name":null,"funder_award_id":"2024M750255","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1950788856","https://openalex.org/W2054041160","https://openalex.org/W2079081961","https://openalex.org/W2146318379","https://openalex.org/W2291567103","https://openalex.org/W2415469094","https://openalex.org/W2510185399","https://openalex.org/W2604321021","https://openalex.org/W2948058585","https://openalex.org/W2950568498","https://openalex.org/W2963076818","https://openalex.org/W2963465695","https://openalex.org/W2964134613","https://openalex.org/W2999259336","https://openalex.org/W3001067654","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3174836262","https://openalex.org/W3203634062","https://openalex.org/W4312757522","https://openalex.org/W4390871852","https://openalex.org/W6738261693","https://openalex.org/W6773520705","https://openalex.org/W6791353385","https://openalex.org/W6801567822","https://openalex.org/W6860784253"],"related_works":["https://openalex.org/W2953562271","https://openalex.org/W2334655667","https://openalex.org/W2464530384","https://openalex.org/W2105938841","https://openalex.org/W4253358700","https://openalex.org/W3139863978","https://openalex.org/W1576128429","https://openalex.org/W4399611050","https://openalex.org/W2269464716","https://openalex.org/W3170431411"],"abstract_inverted_index":{"Skeleton-based":[0],"action":[1],"recognition":[2],"has":[3],"a":[4,80,105,135],"wide":[5],"range":[6],"of":[7,28,39,49,65,97,121],"applications":[8],"in":[9,128],"intelligent":[10],"robotics,":[11],"such":[12],"as":[13,41],"assistance":[14],"for":[15],"the":[16,26,42,47,62,91,126,162,169],"elderly":[17],"and":[18,22,60,72,85,117,145,172],"disabled,":[19],"human-robot":[20],"interaction,":[21],"surveillance.":[23],"Inspired":[24],"by":[25],"success":[27],"vision-language":[29],"pre-trained":[30],"models,":[31],"some":[32],"works":[33],"attempt":[34],"to":[35,45,79,124,155],"employ":[36],"text":[37,53,119],"prompts":[38,54,120],"actions":[40,123],"prior":[43],"knowledge":[44,64],"improve":[46],"performance":[48,167],"models.":[50],"However,":[51],"these":[52],"focus":[55],"more":[56,130],"on":[57,168],"spatial":[58,73,118],"information":[59],"ignore":[61],"temporal":[63,71,95,116],"actions,":[66],"while":[67],"skeleton":[68],"features":[69],"contain":[70],"information.":[74],"This":[75],"not":[76],"only":[77],"leads":[78],"semantic":[81],"gap":[82],"between":[83],"visual":[84],"textual":[86],"modalities":[87],"but":[88],"also":[89],"limits":[90],"model":[92,127],"from":[93],"learning":[94,129],"cues":[96],"actions.":[98],"To":[99],"address":[100],"this":[101,157],"issue,":[102],"we":[103],"propose":[104],"Visual-Language":[106],"Aligned":[107],"spatial-temporal":[108],"Feature":[109],"Enhancement":[110],"framework":[111],"(VLA-FE),":[112],"which":[113,140],"applies":[114],"both":[115],"human":[122],"guide":[125,156],"discriminative":[131],"representations.":[132],"VLA-FE":[133],"adopts":[134],"two-branch":[136],"multi-modal":[137],"training":[138],"strategy,":[139],"is":[141],"decomposed":[142],"into":[143],"spatial-aware":[144],"temporal-aware":[146],"processes.":[147],"Moreover,":[148],"We":[149],"apply":[150],"two":[151],"contrastive":[152],"losses":[153],"correspondingly":[154],"process.":[158],"Experiments":[159],"show":[160],"that":[161],"proposed":[163],"method":[164],"achieves":[165],"promising":[166],"NTU":[170],"RGB+D":[171],"NW-UCLA":[173],"datasets.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}