IP Library Granted Patent US 12,640,249
Granted Patent B2
US 12,640,249 · App. 17/618,269 · Granted May 26, 2026

Method and system for measuring and analyzing body movement, positioning and posture

Inventors: Amin Niri (Vancouver, CA); Connor Gill (Vancouver, CA); Amol Gharat (Burnaby, CA)
Assignee: Flex Artificial Intelligence Inc.
G16H20/30A61B5/1123A61B5/1128A61B5/741A61B5/7435G06T7/75G06V20/46G06V40/23G16H40/63G16H50/20A61B2505/09G06T2207/20132
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,640,249
App. No.
17/618,269
Granted
May 26, 2026
Kind
B2
Abstract

One aspect of the invention provides a computer-based method for providing corrective feedback about exercise form, the method comprising; recording a user performing a specific exercise: evaluating, by the computer, with machine learning, computer vision, or deep learning models that have been previously trained in order to evaluate the form of a user by training on labelled and or unlabeled datasets that consist of: both correct and incorrect exercise form for the different types of exercises being evaluated; identifying the user throughout the video, the exercise type, each repetition of the exercise, the user's errors in form; and then generating, by the computer, corrective feedback for the user on how to improve exercise form for subsequent repetitions; and communicating, via an output device, the corrective feedback to the user.

Claims (68)

1 . A method of generating user feedback from video of a user performing one or more reps of an exercise type, the method comprising:

receiving an exercise type;

selecting a rep detection model from a plurality of rep detection models, wherein the selected rep detection model corresponds to the exercise type;

selecting an error indication model from a plurality of error indication models, wherein the selected error indication model corresponds to the exercise type and comprises a machine learning algorithm trained on videos of individuals performing the exercise type;

receiving a video of a user performing one or more reps of the exercise type;

cropping the video to a specific aspect ratio;

identifying a plurality of frames in the video corresponding to a rep of the exercise type with the selected rep detection model;

generating a form error indication for the rep with the selected error indication model; and

generating feedback based on the form error indication;

wherein generating the form error indication for the detected rep with the selected error indication model comprises:

generating an error indication for each of the plurality of frames corresponding to the rep; and

generating the form error indication based at least in part on the error indication for at least one of the plurality of frames corresponding to the rep.

2 . The method according to claim 1 , wherein receiving the exercise type comprises receiving a user selection of one of a plurality of exercise types.

3 . The method according to claim 1 , wherein receiving the exercise type comprises generating an exercise type for the video with an exercise classification model.

4 . The method according to claim 1 , wherein receiving the video of the user performing one or more reps of the exercise type comprises capturing video of the user performing the reps with a video capture device.

5 . The method according to claim 1 , wherein the specific aspect ratio is one pixel by one pixel.

6 . The method according to claim 1 , wherein the error indication for each frame of the rep comprises an error probability, and generating the form error indication based at least in part on the error indication for at least one frame of the rep comprises generating a form error indication indicating the presence of an error if the error probability for at least one frame of the rep exceeds a probability threshold.

7 . The method according to claim 1 , wherein the error indication for each frame of the rep comprises an error probability, and generating the form error indication based at least in part on the error indication for at least one frame of the rep comprises generating a form error indication indicating the presence of an error if the error probability for a threshold number of frames of the rep exceed a probability threshold.

8 . The method according to claim 1 , wherein the error indication for each frame of the rep comprises an error probability, and generating the form error indication based at least in part on the error indication for at least one frame of the rep comprises generating a form error indication indicating the presence of an error if the error probability for a threshold number of consecutive frames of the rep exceed a probability threshold.

9 . The method according to claim 1 , wherein the error indication for each frame of the rep comprises an error probability, and generating the form error indication based at least in part on the error indication for at least one frame of the rep comprises:

calculating a sum of the error probabilities of the frames of the rep; and

generating a form error indication indicating the presence of an error if the sum of the error probabilities exceeds a probability threshold.

10 . The method according to claim 1 , wherein generating feedback based on the form error indication comprises selecting a media file corresponding to an error type of the error indication model if the form error indication indicates the presence of an error in the rep.

11 . The method according to claim 10 , wherein the media file comprises video of an individual demonstrating an error of the error type.

12 . The method according to claim 10 , wherein the media file comprises corrective audio instructions.

13 . The method according to claim 10 , wherein the media file comprises corrective video instructions.

14 . A non-transitory medium having stored thereon computer-readable instructions, which when executed by a data processor, cause the data processor to execute the method according to claim 5 .

15 . A method according to claim 5 , wherein the exercise type is one of: squats, deadlifts, pull-ups, push-ups, bench presses, planks, bicep curls, and a yoga pose.

16 . The method according to claim 1 , wherein the selected error indication model is configured to identify a body part of the user, and generating the form error indication for the detected rep with the selected error indication model further comprises:

identifying a position of the body part of the user in one of the plurality of frames; and

generating the form error indication based on the position of the body part of the user.

17 . The method according to claim 1 , wherein the selected error indication model is configured to identify an exercise equipment, and generating the form error indication for the detected rep with the selected error indication model further comprises:

identifying the exercise equipment in one of the plurality of frames; and

generating the form error indication based on the identified exercise equipment.

18 . A method of generating user feedback from video of a user performing one or more reps of an exercise type, the method comprising:

receiving an exercise type;

selecting a rep detection model from a plurality of rep detection models, wherein the selected rep detection model corresponds to the exercise type;

selecting an error indication model from a plurality of error indication models, wherein the selected error indication model corresponds to the exercise type and comprises a machine learning algorithm trained on videos of individuals performing the exercise type;

receiving a video of a user performing one or more reps of the exercise type;

adding pixels to the video to format the video to a specific aspect ratio;

identifying a plurality of frames in the video corresponding to a rep of the exercise type with the selected rep detection model;

generating a form error indication for the rep with the selected error indication model; and

generating feedback based on the form error indication;

wherein generating the form error indication for the detected rep with the selected error indication model comprises:

generating an error indication for each of the plurality of frames corresponding to the rep; and

generating the form error indication based at least in part on the error indication for at least one of the plurality of frames corresponding to the rep.

19 . A system for providing feedback to a user performing one or more reps of an exercise type, the system comprising:

a video capture device;

a processor;

a memory module;

an input module; and

an output module;

wherein the processor is configured to:

receive an exercise type;

capture video of the user performing one or more reps of the exercise type with the video capture device;

retrieve a rep detection model corresponding to the exercise type from the memory module;

crop the video to a specific aspect ratio;

execute the rep detection model to identify a plurality of frames in the video corresponding to a rep of the exercise type;

retrieve an error indication model corresponding to the exercise type from the memory module, wherein the error indication model comprises a machine learning algorithm trained on videos of individuals performing the exercise type;

execute the error indication model to generate a form error indication for the identified rep; and

output feedback with the output module based on the form error indication;

wherein the processor is configured to:

execute the error indication model to generate a form error indication for each of the plurality of frames corresponding to the rep; and

generate the form error indication based at least in part on the error indication for at least one of the plurality of frames corresponding to the rep.

20 . The system according to claim 19 , wherein the processor is configured to receive the exercise type from the input module.

21 . The system according to claim 19 , wherein the processor is configured to:

retrieve an exercise classification model from the memory module; and

execute the exercise classification model to generate the exercise type from the video.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 10, 2021
From: NIRI, AMIN; GILL, CONNOR; GHARAT, AMOL
To: FLEX ARTIFICIAL INTELLIGENCE INC.
Reel/Frame 058363/0027 →
Continuity (2)
Provisional Application 62865052 · Jun 21, 2019
Related Publication 20220310226A1 · Sep 29, 2022
References Cited (257)
US 4350336A · Hanford · 1982 [cited by applicant]
US 4533136A · Smith et al. · 1985 [cited by applicant]
US 4591147A · Smith et al. · 1986 [cited by applicant]
US 4695050A · Smith et al. · 1987 [cited by applicant]
US 4790530A · Maag · 1988 [cited by applicant]
US 4822038A · Maag · 1989 [cited by applicant]
US 4838543A · Armstrong et al. · 1989 [cited by applicant]
US 4838548A · Maag · 1989 [cited by applicant]
US 4840373A · Maag · 1989 [cited by applicant]
US 4883270A · Maag · 1989 [cited by applicant]
US 4917379A · Maag · 1990 [cited by applicant]
US 4974831A · Dunham · 1990 [cited by applicant]
US 5007630A · Real et al. · 1991 [cited by applicant]
US 5085426A · Wanzer et al. · 1992 [cited by applicant]
US 5085430A · Habing · 1992 [cited by applicant]
US 5129872A · Dalton et al. · 1992 [cited by applicant]
US 5129873A · Henderson et al. · 1992 [cited by applicant]
US 5190513A · Habing et al. · 1993 [cited by applicant]
US 5199935A · Gibson et al. · 1993 [cited by applicant]
US 5253915A · Schnader et al. · 1993 [cited by applicant]
US 5308304A · Habing · 1994 [cited by applicant]
US 5318490A · Henderson et al. · 1994 [cited by applicant]
US 5320588A · Wanzer et al. · 1994 [cited by applicant]
US 5322491A · Wanzer et al. · 1994 [cited by applicant]
US 5366432A · Habing et al. · 1994 [cited by applicant]
US 5383828A · Sands et al. · 1995 [cited by applicant]
US 5417634A · Habing · 1995 [cited by applicant]
US 5435798A · Habing et al. · 1995 [cited by applicant]
US 5554086A · Habing et al. · 1996 [cited by applicant]
US 5580337A · Habing et al. · 1996 [cited by applicant]
US 5597257A · Habing · 1997 [cited by applicant]
US 5685804A · Whan-Tong et al. · 1997 [cited by applicant]
US 5709632A · Socwell · 1998 [cited by applicant]
US 5803882A · Habing et al. · 1998 [cited by applicant]
US 5885193A · Habing et al. · 1999 [cited by applicant]
US 5897461A · Socwell · 1999 [cited by applicant]
US 5897467A · Habing et al. · 1999 [cited by applicant]
US 5971895A · Habing · 1999 [cited by applicant]
US 6013011A · Moore et al. · 2000 [cited by applicant]
US 6080091A · Habing et al. · 2000 [cited by applicant]
US 6123650A · Birrell · 2000 [cited by applicant]
US 6146313A · Whan-Tong et al. · 2000 [cited by applicant]
US 6162152A · Kuo · 2000 [cited by applicant]
US 6165107A · Birrell · 2000 [cited by applicant]
US 6238321B1 · Arnold et al. · 2001 [cited by applicant]
US 6450967B1 · Wu · 2002 [cited by applicant]
US 6475122B2 · Wu · 2002 [cited by applicant]
US 6478720B1 · Barker · 2002 [cited by applicant]
US 6482130B1 · Pasero et al. · 2002 [cited by applicant]
US 6561952B2 · Wu · 2003 [cited by applicant]
US 6561961B2 · Wu · 2003 [cited by applicant]
US 6589138B2 · Dyer et al. · 2003 [cited by applicant]
US 6677740B1 · Chen et al. · 2004 [cited by applicant]
US 6710491B2 · Wu et al. · 2004 [cited by applicant]
US 6837124B2 · Tsai et al. · 2005 [cited by applicant]
US 6840892B1 · Wu · 2005 [cited by applicant]
US 6846274B2 · Lopez-Santillana et al. · 2005 [cited by applicant]
US 6906503B2 · Lopez-Santillana et al. · 2005 [cited by applicant]
US 6921356B1 · Habing et al. · 2005 [cited by applicant]
US 6939271B1 · Whan-Tong et al. · 2005 [cited by applicant]
US 6942603B1 · Tsai et al. · 2005 [cited by applicant]
US 6945915B2 · Wu · 2005 [cited by applicant]
US 6964614B1 · Tsai · 2005 [cited by applicant]
US 7014597B2 · Tsai · 2006 [cited by applicant]
US 7044893B2 · Tsai · 2006 [cited by applicant]
US 7071589B2 · Bramel et al. · 2006 [cited by applicant]
US 7090623B2 · Stewart et al. · 2006 [cited by applicant]
US 7094180B2 · Huang et al. · 2006 [cited by applicant]
US 7104927B2 · Tsai · 2006 [cited by applicant]
US 7156777B2 · Dyer et al. · 2007 [cited by applicant]
US 7374522B2 · Arnold · 2008 [cited by applicant]
US 7507187B2 · Dyer et al. · 2009 [cited by applicant]
US 7621846B2 · Ainsworth et al. · 2009 [cited by applicant]
US 7691034B2 · May et al. · 2010 [cited by applicant]
US 7704192B2 · Dyer et al. · 2010 [cited by applicant]
US 7708672B2 · Gibson et al. · 2010 [cited by applicant]
US 7731634B2 · Stewart et al. · 2010 [cited by applicant]
US 7731635B2 · Dyer · 2010 [cited by applicant]
US 7747593B2 · Patterson et al. · 2010 [cited by applicant]
US 7758469B2 · Dyer et al. · 2010 [cited by applicant]
US 7758472B2 · Stewart · 2010 [cited by applicant]
US 7780577B2 · Arnold · 2010 [cited by applicant]
US 7815547B2 · Wu · 2010 [cited by applicant]
US 7815554B2 · Gibson et al. · 2010 [cited by applicant]
US 7833133B2 · Stewart et al. · 2010 [cited by applicant]
US 7871357B2 · Gibson et al. · 2011 [cited by applicant]
US 7874963B2 · Grind · 2011 [cited by applicant]
US 7887465B2 · Uffelman · 2011 [cited by applicant]
US 7901323B2 · Olason et al. · 2011 [cited by applicant]
US 7922625B2 · Grind · 2011 [cited by applicant]
US 7951098B2 · Wu et al. · 2011 [cited by applicant]
US 7955219B2 · Birrell et al. · 2011 [cited by applicant]
US 8078426B2 · Pipinich et al. · 2011 [cited by applicant]
US 8105250B2 · Wu · 2012 [cited by applicant]
US 8157706B2 · Ainsworth et al. · 2012 [cited by applicant]
US 8221292B2 · Barker et al. · 2012 [cited by applicant]
US 8303470B2 · Stewart et al. · 2012 [cited by applicant]
US 8317663B2 · Stewart et al. · 2012 [cited by applicant]
US 8556779B2 · Grind · 2013 [cited by applicant]
US 8613689B2 · Dyer et al. · 2013 [cited by applicant]
US 8672814B2 · Hopkins · 2014 [cited by applicant]
US 8827870B2 · Dyer et al. · 2014 [cited by applicant]
US 8862238B2 · Rahimi et al. · 2014 [cited by applicant]
US 8944961B2 · Ainsworth et al. · 2015 [cited by applicant]
US 9161708B2 · Elliott et al. · 2015 [cited by applicant]
US 9174085B2 · Foley et al. · 2015 [cited by applicant]
US 9186537B2 · Arnold et al. · 2015 [cited by applicant]
US 9272181B2 · Arnold et al. · 2016 [cited by applicant]
US 9320937B2 · Thompson · 2016 [cited by applicant]
US 9358426B2 · Aragones et al. · 2016 [cited by applicant]
US 9367668B2 · Flynt et al. · 2016 [cited by applicant]
US 9418571B2 · Younger · 2016 [cited by applicant]
US 9430920B2 · Munro et al. · 2016 [cited by applicant]
US 9586085B2 · Arnold et al. · 2017 [cited by applicant]
US 9589207B2 · Holohan · 2017 [cited by applicant]
US 9597540B2 · Arnold · 2017 [cited by applicant]
US 9636543B2 · Dyer et al. · 2017 [cited by applicant]
US 9724566B2 · Birrell · 2017 [cited by applicant]
US 9761011B2 · Utsunomiya et al. · 2017 [cited by applicant]
US 9953459B2 · Pavlidis et al. · 2018 [cited by applicant]
US 9959517B2 · Mourra · 2018 [cited by applicant]
US 9973814B1 · Henderson et al. · 2018 [cited by applicant]
US 9986415B2 · Cao · 2018 [cited by applicant]
US 9996065B2 · Yang et al. · 2018 [cited by applicant]
US 10065062B2 · Stewart · 2018 [cited by applicant]
US 10176171B1 · Patterson et al. · 2019 [cited by applicant]
US 10343008B2 · Pullins et al. · 2019 [cited by applicant]
US 10395119B1 · Vaden · 2019 [cited by examiner]
US 10466963B2 · Levi et al. · 2019 [cited by applicant]
US 10486016B2 · Robert et al. · 2019 [cited by applicant]
US 10668314B2 · Mayer et al. · 2020 [cited by applicant]
US 10698654B2 · Loughrey et al. · 2020 [cited by applicant]
US 10726738B1 · Li · 2020 [cited by examiner]
US 10792495B2 · Izvorski et al. · 2020 [cited by applicant]
US 10864406B2 · Foley et al. · 2020 [cited by applicant]
US 10898760B2 · Packles et al. · 2021 [cited by applicant]
US 10949658B2 · Brown et al. · 2021 [cited by applicant]
US 11056105B2 · Robinson et al. · 2021 [cited by applicant]
US 11074280B2 · Dobrynin et al. · 2021 [cited by applicant]
US 11141624B2 · Wu · 2021 [cited by applicant]
US 11338190B2 · Evancha et al. · 2022 [cited by applicant]
US 11340925B2 · Mukherjee et al. · 2022 [cited by applicant]
US 11344786B2 · Intonato et al. · 2022 [cited by applicant]
US 20030166434A1 · Lopez-Santillana et al. · 2003 [cited by applicant]
US 20050075850A1 · Wu et al. · 2005 [cited by applicant]
US 20050238182A1 · Shih et al. · 2005 [cited by applicant]
US 20060084422A1 · Huang et al. · 2006 [cited by applicant]
US 20060089238A1 · Huang et al. · 2006 [cited by applicant]
US 20060097038A1 · Huang et al. · 2006 [cited by applicant]
US 20060116247A1 · Dyer et al. · 2006 [cited by applicant]
US 20060135318A1 · Shih et al. · 2006 [cited by applicant]
US 20060281604A1 · Stewart et al. · 2006 [cited by applicant]
US 20070171664A1 · Shih et al. · 2007 [cited by applicant]
US 20070179025A1 · Tsai · 2007 [cited by applicant]
US 20070201727A1 · Birrell et al. · 2007 [cited by applicant]
US 20070239088A1 · Wu · 2007 [cited by applicant]
US 20080161163A1 · Stewart et al. · 2008 [cited by applicant]
US 20130053218A1 · Barker · 2013 [cited by applicant]
US 20130123667A1 · Komatireddy · 2013 [cited by examiner]
US 20130310221A1 · Zuber · 2013 [cited by applicant]
US 20140172460A1 · Kohli · 2014 [cited by applicant]
US 20140205980A1 · Braier · 2014 [cited by examiner]
US 20140257537A1 · Stroupe et al. · 2014 [cited by applicant]
US 20150072797A1 · Sakyo · 2015 [cited by examiner]
US 20150139502A1 · Holohan · 2015 [cited by applicant]
US 20150324636A1 · Bentley · 2015 [cited by examiner]
US 20160256740A1 · Rowe · 2016 [cited by applicant]
US 20160300347A1 · Dunn · 2016 [cited by examiner]
US 20170084007A1 · Rakhshanfar et al. · 2017 [cited by applicant]
US 20170178309A1 · Rakhshanfar et al. · 2017 [cited by applicant]
US 20170319906A1 · Chang et al. · 2017 [cited by applicant]
US 20170368413A1 · Shavit · 2017 [cited by examiner]
US 20180050255A1 · Maani · 2018 [cited by examiner]
US 20180336049A1 · Mukherjee et al. · 2018 [cited by applicant]
US 20190091515A1 · Shavit et al. · 2019 [cited by applicant]
US 20190217144A1 · Petrillo et al. · 2019 [cited by applicant]
US 20190290964A1 · Oren · 2019 [cited by applicant]
US 20190295436A1 · Rubinstein et al. · 2019 [cited by applicant]
US 20210154517A1 · Petrillo et al. · 2021 [cited by applicant]
US 20220108470A1 · Brown et al. · 2022 [cited by applicant]
US 20220108476A1 · Zhang · 2022 [cited by applicant]
US 20220148296A1 · Brown et al. · 2022 [cited by applicant]
US 20240082638A1 · Shah · 2024 [cited by examiner]
CA 2048031A1 · 1992 [cited by applicant]
CA 2253175C · 1999 [cited by applicant]
CA 2236774C · 2005 [cited by applicant]
CA 2687166C · 2009 [cited by applicant]
CA 2689927A1 · 2009 [cited by applicant]
CN 108734104A · 2018 [cited by applicant]
DE 20100276U1 · 2001 [cited by applicant]
DE 20206517U1 · 2002 [cited by applicant]
DE 20213149U1 · 2003 [cited by applicant]
DE 10153895A1 · 2003 [cited by applicant]
DE 20308757U1 · 2003 [cited by applicant]
DE 10247369B3 · 2004 [cited by applicant]
DE 10248035A1 · 2004 [cited by applicant]
DE 10258197A1 · 2004 [cited by applicant]
DE 202005013897U1 · 2005 [cited by applicant]
DE 102004020027A1 · 2005 [cited by applicant]
DE 102005047996A1 · 2006 [cited by applicant]
DE 202006003141U1 · 2006 [cited by applicant]
EP 0956884B1 · 2004 [cited by applicant]
EP 1943997A1 · 2008 [cited by applicant]
EP 1844749B1 · 2009 [cited by applicant]
EP 2177196A1 · 2010 [cited by applicant]
EP 2042146B1 · 2010 [cited by applicant]
EP 2067505B1 · 2011 [cited by applicant]
EP 2383020A1 · 2011 [cited by applicant]
EP 2626114A1 · 2013 [cited by applicant]
EP 3000507A1 · 2016 [cited by applicant]
FR 2869549B1 · 2006 [cited by applicant]
FR 2870074B1 · 2006 [cited by applicant]
GB 2270007B · 1994 [cited by applicant]
GB 2294206B · 1996 [cited by applicant]
GB 2385421B · 2004 [cited by applicant]
GB 2413093A · 2005 [cited by applicant]
GB 2413094A · 2005 [cited by applicant]
GB 2412974B · 2008 [cited by applicant]
GB 2539946B · 2019 [cited by applicant]
JP H10225531A · 1998 [cited by applicant]
JP 2008049171A · 2008 [cited by applicant]
WO 2001011776A1 · 2001 [cited by applicant]
WO 2011130561A1 · 2011 [cited by applicant]
WO 2014145711A1 · 2014 [cited by applicant]
WO 2020028883A1 · 2020 [cited by applicant]
WO 2020129025A1 · 2020 [cited by applicant]
WO 2020188425A1 · 2020 [cited by applicant]
US 5,704,877 A, 01/1998, Henry et al. (withdrawn) [cited by applicant]
Parmar, P. et al., “Measuring the Quality of Exercises”, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Aug. 16, 2016, pp. 2241-2244. [cited by applicant]
Díaz-Pereira, M. Pino. “Automatic recognition and scoring of Olympic rhythmic gymnastic movements”, Human Movement Science, vol. 34, Feb. 4, 2014, pp. 63-80. [cited by applicant]
Kanojia, G. et al., “Attentive Spatio-Temporal Representation Learning for Diving Classification”, 2019 IEEE/CVC Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, Jun. 16, 2019, pp. 2467-247… [cited by applicant]
Zhdanov, P. et al., “Improving Human Action Recognition through Hierarchical Neural Network Classifiiers”, 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, Jul. 8, 2018, pp. 1-7. [cited by applicant]
Baptista, R. et al., “Video-Based Feedback for Assisting Physical Activity”, VISIGRAPP 2017, pp. 274-280, Feb. 25, 2017. [cited by applicant]
Andriluka, M. et al., “2D Human Pose Estimation: New Benchmark and State of the Art Analysis”, IEEE Computer Vision and Pattern Recognition, CVPR, 2014. [cited by applicant]
Gkioxari, G. et al., “Actions and Attributes from Wholes and Parts”, arXiv: 1412.2604, May 2015. [cited by applicant]
Jaiswal. A. et al., “CapsuleGAN: Generative Adversarial Capsule Network”, arXiv: 1802.06167, Feb. 2018. [cited by applicant]
Alonde, R. et al., “Capsules for Object Segmentation”, arXiv: 1804.04241, Apr. 2018. [cited by applicant]
Wei, S. et al., “Convolutional Pose Machines”, IEEE Computer Vision and Pattern Recognition, CVPR, 2016. [cited by applicant]
He, K. et al., “Deep Residual Learning for Image Recognition”, arXiv: 1512.00385, Dec. 2015. [cited by applicant]
Toshev, A. et al., “DeepPose: Human Pose Estimation via Deep Neural Networks”, arXiv: 1312.4659, Aug. 2014. [cited by applicant]
Guler, R. A. et al., “DensePose: Dense Human Pose Estimation In The Wild”, arXiv: 1802.00434, Feb. 2018. [cited by applicant]
Chen, X. et al., “Detect What You Can: Detecting and Representing Objects Using Holistic Models And Body Parts”, CBMM Memo No. 015, Jun. 2014. [cited by applicant]
Cai, Y. et al., “Weakly Supervised Human Body Detection Under Arbitrary Poses”, IEEE International Conference on Image Processing, 2016. [cited by applicant]
Sabour, S. et al., “Dynamic Routing Between Capsules”, arXiv: 1710.09829, Nov. 2017. [cited by applicant]
Ren, S. et al., “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”, arXiv: 1506.01497, Jan. 2016. [cited by applicant]
Lin, T. et al., “Feature Pyramid Networks for Object Detection”, arXiv: 1612.03144, Apr. 2017. [cited by applicant]
Simon, T. et al., “Hand Keypoint Detection in Single Images using Multiview Bootstrapping”, IEEE Computer Vision and Pattern Recognition, CVPR, 2017. [cited by applicant]
Deng, J. et al., “ImageNet: A Large-Scale Hierarchical Image Database”, IEEE Computer Vision and Pattern Recognition, CVPR, 2009. [cited by applicant]
He, K. et al., “Mask R-CNN”, arXiv: 1703.06870, Jan. 2018. [cited by applicant]
Lin, Y. et al., “Microsoft COCO: Common Objects in Context”, arXiv: 14050312, Feb. 2015. [cited by applicant]
Tran, D. et al., “Learning Spatiotemporal Features with 3D Convolutional Networks”, arXiv: 1412.0767, Oct. 2015. [cited by applicant]
Bourdev, L. et al., “Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations”, ICCV, Sep. 2009. [cited by applicant]
Kay, W. et al., “The Kinetics Human Action Video Dataset”, arXiv: 1705.06950, May 2017. [cited by applicant]
Shotton, J. et al., “Real-Time Human Pose Recognition in Parts from Single Depth Images”, Microsoft Research Cambrige & Xbox Incubation, 2011. [cited by applicant]
Cao, Z. et al., “Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields”, arXiv: 1611.08050, Apr. 2017. [cited by applicant]
Girshick, R. et al., “Fast R-CNN”, arXiv: 1504.08083, Sep. 2015. [cited by applicant]
Girshick, R. et al., “Region-based Convolutional Networks for Accurate Object Detection and Segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, May 2015. [cited by applicant]