{"id":"https://openalex.org/W2970978784","doi":"https://doi.org/10.1109/icip.2019.8803564","title":"Multi-Stream Single Shot Spatial-Temporal Action Detection","display_name":"Multi-Stream Single Shot Spatial-Temporal Action Detection","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2970978784","doi":"https://doi.org/10.1109/icip.2019.8803564","mag":"2970978784"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8803564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","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/A5100426111","display_name":"Pengfei Zhang","orcid":"https://orcid.org/0000-0002-8303-8930"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengfei Zhang","raw_affiliation_strings":["University of Massachusetts, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780032","display_name":"Yu Cao","orcid":"https://orcid.org/0000-0001-8624-1099"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":["University of Massachusetts, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077348938","display_name":"Benyuan Liu","orcid":"https://orcid.org/0000-0002-7543-1054"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benyuan Liu","raw_affiliation_strings":["University of Massachusetts, Lowell, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3024","issue":null,"first_page":"3691","last_page":"3695"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9912999868392944,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8131186962127686},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.6936800479888916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6929397583007812},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6785576939582825},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5797222852706909},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5443170070648193},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5362573862075806},{"id":"https://openalex.org/keywords/single-shot","display_name":"Single shot","score":0.47289979457855225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45762690901756287},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43740642070770264},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4283943176269531},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22724118828773499},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10269194841384888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131186962127686},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6936800479888916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6929397583007812},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6785576939582825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5797222852706909},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5443170070648193},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5362573862075806},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.47289979457855225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45762690901756287},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43740642070770264},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4283943176269531},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22724118828773499},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10269194841384888},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/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/icip.2019.8803564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1797109199","https://openalex.org/W1867429401","https://openalex.org/W1923332106","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2105101328","https://openalex.org/W2156303437","https://openalex.org/W2342662179","https://openalex.org/W2519080876","https://openalex.org/W2570343428","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2775727048","https://openalex.org/W2962722947","https://openalex.org/W2962790054","https://openalex.org/W2962803561","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W3106250896","https://openalex.org/W6600983433","https://openalex.org/W6639126518","https://openalex.org/W6682864246","https://openalex.org/W6727074247","https://openalex.org/W6747125892","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4386083130","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W3111737715","https://openalex.org/W2117442182","https://openalex.org/W4391266461","https://openalex.org/W2069571255","https://openalex.org/W2590798552","https://openalex.org/W4293226391"],"abstract_inverted_index":{"We":[0,95],"present":[1],"a":[2,97],"3D":[3,52,130],"Convolutional":[4],"Neural":[5],"Networks":[6],"(CNNs)":[7],"based":[8,54],"single":[9,28],"shot":[10],"detector":[11],"for":[12,45,78],"spatial-temporal":[13],"action":[14,79,92,135],"detection":[15,80,93,136],"tasks.":[16,137],"Our":[17,73],"model":[18,74],"includes:":[19],"(i)":[20],"two":[21,50],"short-term":[22],"appearance":[23],"and":[24,30,42,62,83,132],"motion":[25],"streams,":[26],"with":[27],"RGB":[29,61],"optical":[31,63],"flow":[32,64],"image":[33],"input":[34],"separately,":[35],"in":[36,81,134],"order":[37],"to":[38,66],"capture":[39,67],"the":[40,46,68,102,109,113,117,125],"spatial":[41],"temporal":[43],"information":[44],"current":[47,90],"frame;":[48],"(ii)":[49],"long-term":[51],"ConvNet":[53],"stream,":[55],"working":[56],"on":[57,101],"sequences":[58],"of":[59,99,112,119],"continuous":[60],"images":[65],"context":[69],"from":[70],"past":[71],"frames.":[72],"achieves":[75],"strong":[76],"performance":[77],"video":[82],"can":[84],"be":[85],"easily":[86],"integrated":[87],"into":[88],"any":[89],"two-stream":[91],"methods.":[94,115],"report":[96],"frame-mAP":[98],"71.30%":[100],"challenging":[103],"UCF101-24":[104],"[1]":[105],"actions":[106],"dataset,":[107],"achieving":[108],"state-of-the-art":[110],"result":[111],"one-stage":[114],"To":[116],"best":[118],"our":[120,122],"knowledge,":[121],"work":[123],"is":[124],"first":[126],"system":[127],"that":[128],"combined":[129],"CNN":[131],"SSD":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}