Mar 13, 2016 · To this end, we present a pictorial structure model that exploits high-level information about activities to incorporate higher-order part dependencies by modeling action …

Oct 27, 2017 · The benchmark encompasses three competition tracks focusing on i) single-frame multi-person pose estimation, ii) multi-person pose estimation in videos, and iii) multi-person articulated tracking.

In this work, we introduce the challenging problem of joint multi-person pose estimation and tracking of an un-known number of persons in unconstrained videos.

‪Research Manager at NVIDIA Research‬ - ‪‪Cited by 4,031‬‬ - ‪Digital Human AI Research‬

Apr 25, 2018 · In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation …

In this work, we propose a method that estimates the poses of multiple per-sons in an image in which a person can be occluded by another person or might be truncated. To this end, we consider multi-person pose esti-mation as a joint-to-person association problem.

In this paper we propose a new method for 3D hand pose estima-tion from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling factor, which can be estimated additionally if a prior of the hand size is given.

This iterative scheme can mutually improve action classification and pose estimation in still images and demonstrate the effectiveness of global features for initialization, action-specific models for pose estimation, and action classification with global and pose features.

The repo provides the source code for our CVPR'17 paper for joint mult-person pose estimation and tracking. IEEE Conference on Computer Vision and Pattern Recongnition (CVPR) 2017. The code is tested on Ubuntu 16.04 (64bit) with MATLAB (2016a). $ cmake . -DGUROBI_ROOT_DIR=/path/to/gurobi605/linux64 -DGUROBI_VERSION=60.

Nov 23, 2016 · In this work, we introduce the challenging problem of joint multi-person pose estimation and tracking of an unknown number of persons in unconstrained videos.