• Publications
  • Influence
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science, Environmental Science
    IEEE/CVF Conference on Computer Vision and…
  • 17 November 2017
TLDR
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists.
Entropy rate superpixel segmentation
TLDR
An efficient greedy algorithm for superpixel segmentation is developed by exploiting submodular and mono-tonic properties of the objective function and proving an approximation bound of ½ for the optimality of the solution.
Region Covariance: A Fast Descriptor for Detection and Classification
TLDR
A fast method for computation of covariances based on integral images, and the performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariances matrix.
Coupled Generative Adversarial Networks
TLDR
This work proposes coupled generative adversarial network (CoGAN), which can learn a joint distribution without any tuple of corresponding images, and applies it to several joint distribution learning tasks, and demonstrates its applications to domain adaptation and image transformation.
Learning from Simulated and Unsupervised Images through Adversarial Training
TLDR
This work develops a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors, and makes several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training.
Pedestrian Detection via Classification on Riemannian Manifolds
TLDR
A novel approach for classifying points lying on a connected Riemannian manifold using the geometry of the space of d-dimensional nonsingular covariance matrices as object descriptors.
Covariance Tracking using Model Update Based on Lie Algebra
TLDR
The covariance tracking method does not make any assumption on the measurement noise and the motion of the tracked objects, and provides the global optimal solution, and it is shown that it is capable of accurately detecting the nonrigid, moving objects in non-stationary camera sequences.
Human Detection via Classification on Riemannian Manifolds
TLDR
A novel approach for classifying points lying on a Riemannian manifold by incorporating the a priori information about the geometry of the space.
Fast directional chamfer matching
TLDR
This paper significantly improves the accuracy of chamfer matching while reducing the computational time from linear to sublinear (shown empirically) and incorporates edge orientation information in the matching algorithm such that the resulting cost function is piecewise smooth and the cost variation is tightly bounded.
A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection
TLDR
This paper presents a multi-stream bi-directional recurrent neural network for fine-grained action detection that significantly outperforms state-of-the-art action detection methods on both datasets.
...
1
2
3
4
5
...