• Publications
  • Influence
Real-time grasp detection using convolutional neural networks
TLDR
An accurate, real-time approach to robotic grasp detection based on convolutional neural networks that outperforms state-of-the-art approaches by 14 percentage points and runs at 13 frames per second on a GPU. Expand
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints
TLDR
The main contribution is to explicitly consider the inferred 3D geometry of the whole scene, and enforce consistency of the estimated 3D point clouds and ego-motion across consecutive frames, and outperforms the state-of-the-art for both breadth and depth. Expand
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos
TLDR
This work addresses unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular videos, as cameras are the cheapest, least restrictive and most ubiquitous sensor for robotics. Expand
Efficient Object Detection and Segmentation for Fine-Grained Recognition
TLDR
It is shown that combining this with a state-of-the-art classification algorithm leads to significant improvements in performance especially for datasets which are considered particularly hard for recognition, e.g. birds species. Expand
Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras
TLDR
This work is the first to learn the camera intrinsic parameters, including lens distortion, from video in an unsupervised manner, thereby allowing us to extract accurate depth and motion from arbitrary videos of unknown origin at scale. Expand
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
TLDR
The DVN framework achieves the state-of-the-art results on multi-label prediction and image segmentation benchmarks. Expand
Real-Time Pedestrian Detection with Deep Network Cascades
TLDR
This paper presents a new real-time approach to object detection that exploits the efficiency of cascade classifiers with the accuracy of deep neural networks, and applies it to the challenging task of pedestrian detection. Expand
Pruning training sets for learning of object categories
TLDR
This work proposes a fully automatic mechanism for noise cleaning, called 'data pruning', and demonstrates its success on learning of human faces and shows that data pruning can improve on generalization performance for algorithms with various robustness to noise. Expand
Learning and prediction of slip from visual information
TLDR
An approach for slip prediction from a distance for wheeled ground robots using visual information as input using terrain type recognition and nonlinear regression modeling for improved navigation on steep slopes and rough terrain for Mars rovers. Expand
Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation
TLDR
The main idea here is to actively consider the labels or misclassification cost while constructing the classifier, which achieves a good trade-off between recognition performance and speedup on data collected by an autonomous robot. Expand
...
1
2
3
4
5
...