• Publications
  • Influence
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
tl;dr
In this work we study the use of 3D hand poses to recognize first-person dynamic hand actions interacting with 3D objects. Expand
  • 109
  • 14
  • Open Access
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
tl;dr
We investigate the top 10 state-of-the-art methods on three tasks: single frame 3D pose estimation, 3D hand tracking, and hand pose estimation during object interaction. Expand
  • 120
  • 9
  • Open Access
The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation
tl;dr
We present the 2017 Hands in the Million Challenge, a public competition designed for the evaluation of the task of 3D hand pose estimation. Expand
  • 32
  • 6
  • Open Access
Multiple Object Tracking: A Review
tl;dr
Multiple Object Tracking (MOT) is an important computer vision task which has gained increasing attention due to its academic and commercial potential. Expand
  • 71
  • 4
  • Open Access
MCBoost: Multiple Classifier Boosting for Perceptual Co-clustering of Images and Visual Features
tl;dr
We present a new co-clustering problem of images and visual features. Expand
  • 53
  • 3
  • Open Access
Fast violence detection in video
tl;dr
This work proposes a novel method for violence detection in movies based on extreme acceleration patterns as the main feature. Expand
  • 66
  • 2
  • Open Access
Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games
tl;dr
We introduce a cooperative-game theoretical framework called extended convex game (ECG) that is a superset of global reward game and propose a local reward approach called Shapley Q-value. Expand
  • 2
  • 2
  • Open Access
Folding Clothes Autonomously: A Complete Pipeline
tl;dr
This work presents a complete pipeline for folding a pile of clothes using a dual-armed robot using the framework of active random forests to detect grasp points. Expand
  • 34
  • 1
  • Open Access
Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
tl;dr
We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with a wide range of expressions, poses, and illuminations conditioned by synthetic images sampled from a 3D morphable model. Expand
  • 25
  • 1
  • Open Access
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection
tl;dr
We introduce a novel method called transitions forests, an ensemble of decision trees that both learn to discriminate static poses and transitions between pairs of two independent frames. Expand
  • 28
  • Open Access