PPT-Compositional Human Pose Regression

Xiao Sun Joint work with Yichen Wei Human Pose Estimation Problem localize key points of a person Input a single RGB image Output 2D or 3D key points Pose Estimator RGB Image person centered. Rather than modeling articulation using a family of warped rotated and foreshortened templates we use a mixture of small nonoriented parts We describe a general 64258exible mixture model that jointly captures spatial relations between part locations edu Abstract We present a fast and accurate algorithm for comput ing the 2D pose of objects in images called cascaded pose regression CPR CPR progressively re64257nes a loosely spec i64257ed initial guess where each re64257nement is carried out by a Unleashing the Power of Alternation. Patrice Godefroid, Aditya V. Nori, Sriram K. Rajamani. Microsoft Research. Sai Deep Tetali. UC Los Angeles. Property checking. void f(). {. 0:. *p = 4;. 1:. *q . Componen. t-. Based Information Systems. Jan Martijn van der Werf. Organizations cooperate. Bob. Charley. Alice. “Who-knows-who” not transitive!. Dave. Organizations deliver services. Bob. Charley. Recognition. (CVPR’04). Greg Mori, . Xiaofeng. . Ren. , Alexei A. . Efros. and . Jitendra. . Malik. - Pose primitive based human action . recognition in videos or still . images. (CVPR’08). Christian . Yao Li . Fei-Fei. Computer Science Department, Stanford University, USA. Modeling Mutual Context of Object and Human Pose. in Human-Object Interaction Activities. Introduction. Modeling mutual context of object and pose. Used by Kinect. Accurate when the pose closely matches a stored pose. Inaccurate when novel poses are made. Can often produce shaky movement due to pose snapping. 3d Pose Tracking. Calculate poses based on previous poses and current data. Bangpeng Yao and Li Fei-Fei. Computer Science Department, Stanford University. {bangpeng,feifeili}@cs.stanford.edu. 1. Robots interact with objects. Automatic sports commentary. “Kobe is dunking the ball.”. Pelvic Tilt. 3. Bridge Pose. 4. Rocking. 5. Little Boat Twist. 6. Cat. 7. Swan. 8. Table Balancing Pose. 9. Thread the Needle. 10. Cobra. 11 . Corpse. Rocking. Swan. 1. 2. 3. 4. 5. 6. 7. 8. 9. 0. 1. Chair. Yao Lu. Outline. Overview of RGB-D images and sensors. Recognition: human pose, hand gesture. Reconstruction: Kinect fusion. Outline. Overview of RGB-D images and sensors. Recognition: human pose, hand gesture. Bangpeng Yao and Li Fei-Fei. Computer Science Department, Stanford University. {bangpeng,feifeili}@cs.stanford.edu. 1. Robots interact with objects. Automatic sports commentary. “Kobe is dunking the ball.”. Xiao Sun. https://jimmysuen.github.io./. Microsoft Research Asia. Visual Computing Group. Human Pose Estimation. Problem: localize key points of a person. Input: a single RGB image. Output: 2D or 3D key points. Rendevous. using CNN. Ryan McKennon-Kelly. Sharma, . Sumant. , Connor . Beierle. , and Simone D’Amico. “Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networks,” September 19, 2018. . 2019.3.15. HOI. 问题. 定义. HOI—Human-Object. . Interaction. HOI-. D. et. 问题. 定义. HOI—Human-Object. . Interaction. 主语. ->Human. 宾语. ->Object. 谓语. ->. . Action.