• Publications
  • Influence
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion
TLDR
We present data obtained using a hardware system that is able to capture synchronized video and ground-truth 3D motion. Expand
  • 820
  • 135
  • PDF
HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion
TLDR
In this report we present a novel dataset obtained using a unique setup for capturing synchronized video and ground-truth 3D motion. Expand
  • 432
  • 57
  • PDF
A Quantitative Evaluation of Video-based 3D Person Tracking
TLDR
The Bayesian estimation of 3D human motion from video sequences is quantitatively evaluated using synchronized, multi-camera, calibrated video and 3D ground truth poses acquired with a commercial motion capture system. Expand
  • 190
  • 36
  • PDF
Tracking loose-limbed people
TLDR
We pose the problem of 3D human tracking as one of inference in a graphical model. Expand
  • 361
  • 30
  • PDF
Learning Activity Progression in LSTMs for Activity Detection and Early Detection
TLDR
In this work we improve training of temporal deep models to better learn activity progression for activity detection and early detection tasks. Expand
  • 247
  • 29
  • PDF
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
TLDR
This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Expand
  • 378
  • 22
  • PDF
Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation
TLDR
We introduce a novel approach for articulated 2D body pose estimation that uses occlusion-sensitive local image likelihoods that approximate the global image likelihood by accounting for occlusions and do a quantitatively better job of explaining image evidence. Expand
  • 260
  • 21
  • PDF
Detailed Human Shape and Pose from Images
TLDR
We address the problem of markerless human shape and pose capture from multi-camera video sequences using a richly detailed graphics model of 3D human shape that is learned from a database of range scans of human bodies. Expand
  • 311
  • 17
  • PDF
High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
TLDR
The least absolute shrinkage and selection operator (Lasso) allows computationally efficient feature selection based on linear dependency between input features and output values. Expand
  • 138
  • 17
  • PDF
Skin color-based video segmentation under time-varying illumination
TLDR
A novel approach for real-time skin color segmentation in video sequences is described. Expand
  • 277
  • 15
  • PDF