{"id":"https://openalex.org/W4403780518","doi":"https://doi.org/10.1145/3664647.3681664","title":"Vi2ACT:Video-enhanced Cross-modal Co-learning with Representation Conditional Discriminator for Few-shot Human Activity Recognition","display_name":"Vi2ACT:Video-enhanced Cross-modal Co-learning with Representation Conditional Discriminator for Few-shot Human Activity Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780518","doi":"https://doi.org/10.1145/3664647.3681664"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5100333950","display_name":"Kang Xia","orcid":"https://orcid.org/0000-0002-5453-0643"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kang Xia","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004218295","display_name":"Wenzhong Li","orcid":"https://orcid.org/0000-0002-9199-3655"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhong Li","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102624958","display_name":"Yimiao Shao","orcid":"https://orcid.org/0009-0002-5956-6159"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimiao Shao","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043533769","display_name":"Sanglu Lu","orcid":"https://orcid.org/0000-0003-1467-4519"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanglu Lu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100333950"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55435581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1848","last_page":"1856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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":0.9987999796867371,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9970999956130981,"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":0.9968000054359436,"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/discriminator","display_name":"Discriminator","score":0.8246526122093201},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7328166961669922},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7018192410469055},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6245445013046265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6064841151237488},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5837790966033936},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4391767382621765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37757766246795654},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34746402502059937},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06421887874603271},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06302377581596375}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8246526122093201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328166961669922},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7018192410469055},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6245445013046265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064841151237488},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5837790966033936},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4391767382621765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37757766246795654},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34746402502059937},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06421887874603271},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06302377581596375},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2002261403","https://openalex.org/W2200813474","https://openalex.org/W2668061517","https://openalex.org/W2753992112","https://openalex.org/W2783358183","https://openalex.org/W2953033606","https://openalex.org/W2962834855","https://openalex.org/W2963521811","https://openalex.org/W2972376155","https://openalex.org/W3033804066","https://openalex.org/W3083281679","https://openalex.org/W3093184726","https://openalex.org/W3099025572","https://openalex.org/W3119372205","https://openalex.org/W3128981305","https://openalex.org/W3152187098","https://openalex.org/W3156725333","https://openalex.org/W3175647370","https://openalex.org/W3193597430","https://openalex.org/W3200883581","https://openalex.org/W4200416643","https://openalex.org/W4214843096","https://openalex.org/W4220693285","https://openalex.org/W4282928124","https://openalex.org/W4284897674","https://openalex.org/W4294891660","https://openalex.org/W4294891903","https://openalex.org/W4361771086","https://openalex.org/W4387579682"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W1608433645","https://openalex.org/W2964074194"],"abstract_inverted_index":{"Human":[0],"Activity":[1],"Recognition":[2],"(HAR)":[3],"as":[4,25,148,162,164],"an":[5],"emerging":[6],"research":[7],"field":[8],"has":[9],"attracted":[10],"widespread":[11],"academic":[12],"attention":[13],"due":[14],"to":[15,48,50,70,90,113,145],"its":[16],"wide":[17],"range":[18],"of":[19,36,54,74,98],"practical":[20],"applications":[21],"in":[22,187],"areas":[23],"such":[24],"healthcare,":[26],"environmental":[27],"monitoring,":[28],"and":[29,42,119],"sports":[30],"training.":[31],"Given":[32],"the":[33,52,72,106,127,158],"high":[34],"cost":[35],"annotating":[37],"sensor":[38],"data,":[39],"many":[40],"unsupervised":[41],"semi-supervised":[43],"methods":[44],"have":[45],"been":[46],"applied":[47],"HAR":[49,125,174],"alleviate":[51],"problem":[53],"limited":[55],"data.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,123],"propose":[61],"a":[62,79,86,95,137],"novel":[63,138],"video-enhanced":[64],"cross-modal":[65,110],"collaborative":[66],"learning":[67],"method,":[68],"Vi2ACT,":[69],"address":[71],"issue":[73],"few-shot":[75,189],"HAR.":[76],"We":[77,135,166],"introduce":[78],"new":[80],"data":[81],"augmentation":[82],"approach":[83],"that":[84,142,180],"utilizes":[85],"text-to-video":[87],"generation":[88],"model":[89],"generate":[91],"class-related":[92],"videos.":[93],"Subsequently,":[94],"large":[96],"quantity":[97],"video":[99,107,116,151],"semantic":[100,117],"representations":[101,118,152],"are":[102],"obtained":[103],"through":[104],"fine-tuning":[105],"encoder":[108,161],"for":[109],"co-learning.":[111],"Furthermore,":[112],"effectively":[114],"align":[115],"time":[120,159],"series":[121,160],"representations,":[122],"enhance":[124],"at":[126],"representation-level":[128],"using":[129],"conditional":[130],"Generative":[131],"Adversarial":[132],"Nets":[133],"(cGAN).":[134],"design":[136],"Representation":[139],"Conditional":[140],"Discriminator":[141],"is":[143],"trained":[144],"assess":[146],"samples":[147],"originating":[149],"from":[150],"rather":[153],"than":[154],"those":[155],"generated":[156],"by":[157],"accurately":[163],"possible.":[165],"conduct":[167],"extensive":[168],"experiments":[169],"on":[170],"four":[171],"commonly":[172],"used":[173],"datasets.":[175],"The":[176],"experimental":[177],"results":[178],"demonstrate":[179],"our":[181],"method":[182],"outperforms":[183],"other":[184],"baseline":[185],"models":[186],"all":[188],"scenarios.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}