AI News,

My area of expertise is three dimensional (3D) computer vision, specifically using high accuracy range sensors such as laser scanners for problems in the areas of modeling, recognition, and visualization.

The ability to reverse engineer buildings has enormous potential benefit in a variety of fields, ranging from robotics to civil engineering to homeland security.

Fellows

I am fascinated by the basic physical learning processes that take place in nature at the micro-scale (e.g.

Chaohui Wang

To this end, we first introduce a joint 2.5D layered model where top-down object-level and bottom-up pixel-level representations are seamlessly combined through local constraints that involve only pairs of variables, as opposed to previous 2.5D layered models where the depth ordering was commonly modeled as a total and strict order between all the objects.

3D Computer Vision: Past, Present, and Future

Google Tech Talk August 15, 2011 Presented by Steve Seitz ABSTRACT 3D Computer Vision: Past, Present, and Future.

Computer Vision and Machine Learning, by Nick Wong

A basic introduction to some fundamental concepts in machine learning using Tensorflow, coupled with an introduction to OpenCV2, a computer vision project.

Lecture 11 | Detection and Segmentation

In Lecture 11 we move beyond image classification, and show how convolutional networks can be applied to other core computer vision tasks. We show how fully convolutional networks equipped...

Simple paper sheet tracking with a Kalman filter and edge detection

I am starting to work with vision based tracking again (object and camera tracking), hoping to continue my doctorate research, and also create some nice "demo" videos of my work. I am using...

Visual 3D modeling of real-world objects and scenes from...

Google Tech Talks May 1, 2007 ABSTRACT Images and videos form a rich source of information about the visual world. The extraction of 3D information from images is an important research problem...

Small Deep Neural Networks - Their Advantages, and Their Design

Deep neural networks (DNNs) have led to significant improvements to the accuracy of machine-learning applications. For many problems, such as object classification and object detection, DNNs...

Lecture 12 | Visualizing and Understanding

In Lecture 12 we discuss methods for visualizing and understanding the internal mechanisms of convolutional networks. We also discuss the use of convolutional networks for generating new images,...

Lecture 9 | CNN Architectures

In Lecture 9 we discuss some common architectures for convolutional neural networks. We discuss architectures which performed well in the ImageNet challenges, including AlexNet, VGGNet, GoogLeNet,...

Visualizing Data Using t-SNE

Google Tech Talk June 24, 2013 (more info below) Presented by Laurens van der Maaten, Delft University of Technology, The Netherlands ABSTRACT Visualization techniques are essential tools...

Temporal Action Co-Segmentation in 3D Motion Capture Data & Videos (CVPR 2017)

Given two action sequences, we are interested in spotting/co-segmenting all pairs of sub-sequences that represent the same action. We propose a totally unsupervised solution to this problem....