{"id":"https://openalex.org/W2981342841","doi":"https://doi.org/10.1145/3343031.3351054","title":"Sparse Temporal Causal Convolution for Efficient Action Modeling","display_name":"Sparse Temporal Causal Convolution for Efficient Action Modeling","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981342841","doi":"https://doi.org/10.1145/3343031.3351054","mag":"2981342841"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5048152070","display_name":"Changmao Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changmao Cheng","raw_affiliation_strings":["Fudan University & Jilian Technology Group (Video++), Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University & Jilian Technology Group (Video++), Shanghai, China","institution_ids":["https://openalex.org/I4210099297","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111265785","display_name":"Chi Zhang","orcid":"https://orcid.org/0009-0000-0323-0715"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Megvii Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Megvii Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081897818","display_name":"Yichen Wei","orcid":"https://orcid.org/0000-0002-3593-8280"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Wei","raw_affiliation_strings":["Megvii Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Megvii Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University & Jilian Technology Group (Video++), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Fudan University & Jilian Technology Group (Video++), Beijing, China","institution_ids":["https://openalex.org/I4210099297","https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048152070"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210099297"],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84707047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"592","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9966999888420105,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009477615356445},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6636942625045776},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5092798471450806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35534876585006714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3312166929244995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009477615356445},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6636942625045776},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5092798471450806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35534876585006714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312166929244995},{"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},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"},{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W28988658","https://openalex.org/W1520997877","https://openalex.org/W1522734439","https://openalex.org/W1595717062","https://openalex.org/W1677182931","https://openalex.org/W1923404803","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2020163092","https://openalex.org/W2024868105","https://openalex.org/W2033959528","https://openalex.org/W2063153269","https://openalex.org/W2105101328","https://openalex.org/W2108333036","https://openalex.org/W2126579184","https://openalex.org/W2161565164","https://openalex.org/W2342662179","https://openalex.org/W2401640538","https://openalex.org/W2507009361","https://openalex.org/W2526479943","https://openalex.org/W2553594924","https://openalex.org/W2601564443","https://openalex.org/W2625366777","https://openalex.org/W2626778328","https://openalex.org/W2738136547","https://openalex.org/W2746726611","https://openalex.org/W2761659801","https://openalex.org/W2766187676","https://openalex.org/W2770804203","https://openalex.org/W2795783309","https://openalex.org/W2798592524","https://openalex.org/W2806676437","https://openalex.org/W2883429621","https://openalex.org/W2895387432","https://openalex.org/W2897550429","https://openalex.org/W2897683730","https://openalex.org/W2949309701","https://openalex.org/W2950673314","https://openalex.org/W2952186347","https://openalex.org/W2952453038","https://openalex.org/W2962743139","https://openalex.org/W2962824366","https://openalex.org/W2962835968","https://openalex.org/W2963091558","https://openalex.org/W2963125871","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963677766","https://openalex.org/W2964054038","https://openalex.org/W2964265128"],"related_works":["https://openalex.org/W303980170","https://openalex.org/W2351491280","https://openalex.org/W3034099097","https://openalex.org/W2386767533","https://openalex.org/W2371447506","https://openalex.org/W2333698505","https://openalex.org/W3135881253","https://openalex.org/W2068395868","https://openalex.org/W2041344627","https://openalex.org/W4251415830"],"abstract_inverted_index":{"Recently,":[0],"spatio-temporal":[1],"convolutional":[2,35],"networks":[3,38],"have":[4],"achieved":[5],"prominent":[6],"performance":[7],"in":[8,37],"action":[9,41,102],"classification.":[10],"However,":[11],"debates":[12],"on":[13,114],"the":[14,21,46,75,99,111],"importance":[15],"of":[16,23,101],"temporal":[17,34,48,67],"information":[18],"lead":[19],"to":[20,31],"rethinking":[22],"these":[24],"architectures.":[25],"In":[26],"this":[27],"work,":[28],"we":[29,62,73],"propose":[30],"employ":[32],"sparse":[33],"operations":[36],"for":[39,66,97],"efficient":[40],"modeling.":[42],"We":[43],"demonstrate":[44],"that":[45],"explicit":[47],"feature":[49,68],"interactions":[50],"can":[51],"be":[52],"largely":[53],"reduced":[54],"without":[55],"any":[56],"degradation.":[57],"And":[58],"towards":[59],"better":[60],"scalability,":[61],"use":[63],"causal":[64],"convolutions":[65],"learning.":[69],"Under":[70],"causality":[71],"constraints,":[72],"replenish":[74],"model":[76,107],"with":[77],"auxiliary":[78],"self-supervised":[79],"tasks,":[80],"namely":[81],"video":[82],"prediction":[83],"and":[84,119],"frame":[85],"order":[86],"discrimination.":[87],"Besides,":[88],"a":[89],"gradient":[90],"based":[91],"multi-task":[92],"learning":[93],"algorithm":[94],"is":[95],"introduced":[96],"guaranteeing":[98],"dominance":[100],"recognition":[103],"task.":[104],"The":[105],"proposed":[106],"matches":[108],"or":[109],"outperforms":[110],"state-of-the-art":[112],"methods":[113],"Kinetics,":[115],"Something-Something":[116],"V2,":[117],"UCF101":[118],"HMDB51":[120],"datasets.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}