{"id":"https://openalex.org/W3092651603","doi":"https://doi.org/10.1145/3394171.3413641","title":"A Slow-I-Fast-P Architecture for Compressed Video Action Recognition","display_name":"A Slow-I-Fast-P Architecture for Compressed Video Action Recognition","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092651603","doi":"https://doi.org/10.1145/3394171.3413641","mag":"3092651603"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413641","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413641","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100676609","display_name":"Jiapeng Li","orcid":"https://orcid.org/0000-0001-6091-3141"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiapeng Li","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947241","display_name":"Ping Wei","orcid":"https://orcid.org/0000-0002-8535-9527"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wei","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070113956","display_name":"Yongchi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongchi Zhang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100676609"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":2.7479,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92144479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2039","last_page":"2047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9973000288009644,"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":0.9957000017166138,"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":0.8340480327606201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7036363482475281},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5511797666549683},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5371729731559753},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5204039812088013},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.465433269739151},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4591189920902252},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45538002252578735},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.4419757127761841},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.44028618931770325},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25759321451187134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340480327606201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7036363482475281},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5511797666549683},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5371729731559753},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5204039812088013},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.465433269739151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4591189920902252},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45538002252578735},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.4419757127761841},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.44028618931770325},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25759321451187134},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413641","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394171.3413641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413641","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G577169378","display_name":null,"funder_award_id":"2018AAA0102501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G819162044","display_name":null,"funder_award_id":"61876149","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092651603.pdf","grobid_xml":"https://content.openalex.org/works/W3092651603.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W764651262","https://openalex.org/W1513100184","https://openalex.org/W1522734439","https://openalex.org/W1594551768","https://openalex.org/W1979741733","https://openalex.org/W1996822428","https://openalex.org/W2045192497","https://openalex.org/W2098580305","https://openalex.org/W2115907784","https://openalex.org/W2126579184","https://openalex.org/W2132529238","https://openalex.org/W2154504070","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2342662179","https://openalex.org/W2342776425","https://openalex.org/W2416798379","https://openalex.org/W2507009361","https://openalex.org/W2548527721","https://openalex.org/W2560474170","https://openalex.org/W2566769621","https://openalex.org/W2746726611","https://openalex.org/W2751023760","https://openalex.org/W2782776028","https://openalex.org/W2799176631","https://openalex.org/W2883429621","https://openalex.org/W2883534172","https://openalex.org/W2884797191","https://openalex.org/W2913397815","https://openalex.org/W2934628279","https://openalex.org/W2947084868","https://openalex.org/W2951933753","https://openalex.org/W2952005526","https://openalex.org/W2962864875","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963216700","https://openalex.org/W2963370182","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963775820","https://openalex.org/W2963782415","https://openalex.org/W2963820951","https://openalex.org/W2963886665","https://openalex.org/W2963891416","https://openalex.org/W2963901365","https://openalex.org/W2964297311","https://openalex.org/W2981385151","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W2990541775"],"related_works":["https://openalex.org/W2171116555","https://openalex.org/W2283162247","https://openalex.org/W4212983513","https://openalex.org/W4281553171","https://openalex.org/W2524507886","https://openalex.org/W2314488738","https://openalex.org/W3172812035","https://openalex.org/W2621092033","https://openalex.org/W3088596192","https://openalex.org/W2755343736"],"abstract_inverted_index":{"Compressed":[0],"video":[1,61],"action":[2,62],"recognition":[3],"has":[4],"drawn":[5],"growing":[6],"attention":[7],"for":[8,59],"the":[9,22,67,78,112,115,137,151,156],"storage":[10],"and":[11,43,77,94,140,147,153],"processing":[12],"advantages":[13],"of":[14,66,155],"compressed":[15,60,107],"videos":[16,42],"over":[17],"original":[18],"raw":[19,41,121],"videos.":[20,108,122],"While":[21],"past":[23],"few":[24],"years":[25],"have":[26],"witnessed":[27],"remarkable":[28],"progress":[29],"in":[30,106,127],"this":[31,48],"problem,":[32],"most":[33],"existing":[34],"approaches":[35],"rely":[36],"on":[37,114,136],"RGB":[38],"frames":[39],"from":[40,120],"require":[44],"multi-step":[45],"training.":[46],"In":[47],"paper,":[49],"we":[50],"propose":[51],"a":[52,72,83,95],"novel":[53],"Slow-I-Fast-P":[54],"(SIFP)":[55],"neural":[56],"network":[57],"model":[58,110,124],"recognition.":[63],"It":[64],"consists":[65],"slow":[68],"I":[69],"pathway":[70,81],"receiving":[71,82],"sparse":[73],"sampling":[74,85],"I-frame":[75],"clip":[76],"fast":[79],"P":[80],"dense":[84],"pseudo":[86,103],"optical":[87,104,117],"flow":[88],"clip.":[89],"An":[90],"unsupervised":[91],"estimation":[92],"method":[93,133],"new":[96],"loss":[97],"function":[98],"are":[99],"designed":[100],"to":[101],"generate":[102],"flows":[105,118],"Our":[109],"eliminates":[111],"dependence":[113],"traditional":[116],"calculated":[119],"The":[123,131,143],"is":[125,134],"trained":[126],"an":[128],"end-to-end":[129],"way.":[130],"proposed":[132,157],"evaluated":[135],"challenging":[138],"HMDB51":[139],"UCF101":[141],"datasets.":[142],"extensive":[144],"comparison":[145],"results":[146],"ablation":[148],"studies":[149],"demonstrate":[150],"effectiveness":[152],"strength":[154],"method.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}