{"id":"https://openalex.org/W4387969137","doi":"https://doi.org/10.1145/3581783.3612490","title":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","display_name":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969137","doi":"https://doi.org/10.1145/3581783.3612490"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612490","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5102850945","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-5875-7511"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5875-7511","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065572304","display_name":"Junlong Du","orcid":"https://orcid.org/0009-0004-0288-4652"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Du","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-0288-4652","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967246","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0003-3424-4866"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Yan","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3424-4866","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3175-3553","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5339","last_page":"5347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8353283405303955},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.7396801114082336},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6771063208580017},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6753705739974976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5929108262062073},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5399937033653259},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5362047553062439},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4987642765045166},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47077202796936035},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4582883417606354},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4518806040287018},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4202452301979065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.348436176776886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353283405303955},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7396801114082336},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6771063208580017},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6753705739974976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929108262062073},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5399937033653259},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5362047553062439},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4987642765045166},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47077202796936035},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4582883417606354},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4518806040287018},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4202452301979065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.348436176776886},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612490","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":34,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2126579184","https://openalex.org/W2145215286","https://openalex.org/W2520613337","https://openalex.org/W2562153041","https://openalex.org/W2724511873","https://openalex.org/W2740825418","https://openalex.org/W2883429621","https://openalex.org/W2904378456","https://openalex.org/W2962714319","https://openalex.org/W2962914678","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963218601","https://openalex.org/W2963785020","https://openalex.org/W2963820951","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3035254087","https://openalex.org/W3035303837","https://openalex.org/W3198377975","https://openalex.org/W3210279979","https://openalex.org/W4214555767","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214727094","https://openalex.org/W4214746887","https://openalex.org/W4226058394","https://openalex.org/W4312310776","https://openalex.org/W4312560592","https://openalex.org/W4312658081","https://openalex.org/W4312818263"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W4388696151","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566"],"abstract_inverted_index":{"The":[0],"Contrastive":[1],"Language-Image":[2],"Pre-training":[3],"(CLIP)":[4],"has":[5,14],"recently":[6],"shown":[7],"remarkable":[8],"generalization":[9],"on":[10,120,137,147],"\"zero-shot\"":[11,140],"training":[12,149],"and":[13,31,65,111,123,139,155],"applied":[15],"to":[16,26,62,80,86,106],"many":[17],"downstream":[18],"tasks.":[19],"We":[20,36,116,142],"explore":[21],"the":[22,39,45,69,74,114],"adaptation":[23],"of":[24],"CLIP":[25],"achieve":[27,107,144],"a":[28,57,82,102,108,134],"more":[29],"efficient":[30],"generalized":[32],"action":[33],"recognition":[34],"method.":[35],"propose":[37,101],"that":[38,53],"key":[40],"lies":[41],"in":[42,49],"explicitly":[43],"modeling":[44,60],"motion":[46,59,64,76],"cues":[47,77],"flowing":[48],"video":[50],"frames.":[51],"To":[52],"end,":[54],"we":[55,100],"design":[56],"two-stream":[58],"block":[61,105],"capture":[63],"spatial":[66],"information":[67,94],"at":[68],"same":[70],"time.":[71],"And":[72],"then,":[73],"obtained":[75],"are":[78],"utilized":[79],"drive":[81],"dynamic":[83],"prompts":[84],"learner":[85],"generate":[87],"motion-aware":[88],"prompts,":[89],"which":[90],"contain":[91],"much":[92],"semantic":[93],"concerning":[95],"human":[96],"actions.":[97],"In":[98],"addition,":[99],"multimodal":[103],"communication":[104],"collaborative":[109],"learning":[110],"further":[112],"improve":[113],"performance.":[115],"conduct":[117],"extensive":[118],"experiments":[119],"HMDB-51,":[121],"UCF-101,":[122],"Kinetics-400":[124],"datasets.":[125],"Our":[126],"method":[127],"outperforms":[128],"most":[129],"existing":[130],"state-of-the-art":[131],"methods":[132],"by":[133],"significant":[135],"margin":[136],"\"few-shot\"":[138],"training.":[141],"also":[143],"competitive":[145],"performance":[146],"\"closed-set\"":[148],"with":[150],"extremely":[151],"few":[152],"trainable":[153],"parameters":[154],"additional":[156],"computational":[157],"costs.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}