No abstract

Factorization network Te s t Train ϕ 3D shape and viewpoint (α, θ ) (Y, v) 2D keypoints and visibility Dense keypoints Non-rigid objects Rigid objects Monocular reconstruction of:ϕ Figure 1: Our method learns a 3D model of a deformable object category from 2D keypoints in unconstrained images. It comprises a deep network that learns to factorize shape and viewpoint and, at test time, performs monocular reconstruction. AbstractWe propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, there exists a certain canonicalization function of the reconstructed shapes. Then, we learn the canonicalization function together with the reconstruction one, which constrains the result to be consistent. We demonstrate stateof-the-art reconstruction results for methods that do not use ground-truth 3D supervision for a number of benchmarks, including Up3D and PASCAL3D+. Source code has been made available at https

Convolutional neural networks (CNNs) are powerful tools for understanding data with spatial structure such as photos. They are most commonly used in two dimensions, but they can also be applied more generally. One-dimensional CNNs are used for processing time-series such as human speech. Three dimensional CNNs have been used to analyze movement in 2+1 dimensional space-time [2] and for helping drones find a safe place to land [3]. Three dimensional convolutional deep belief networks have been used to recognize objects in 2.5D depth maps [4].In [1], a sparse two-dimensional CNN is implemented to perform Chinese handwriting recognition. When a handwritten character is rendered at moderately high resolution on a two dimensional grid, it looks like a sparse matrix. If we only calculate the hidden units of the CNN that can actually see some part of the input field the pen has visited, the workload decreases.Sparsity is a useful optimization in two dimensions, and it is potentially even more useful in three or higher dimensions. This is related to the curse of dimensionality; an N × N × N cubic grid contains many more points than an N × N square grid. We have adapted the algorithm from [1] to implement sparse CNNs on range of different graphs. CUDA GPU code for running sparse 2, 3 and 4 dimensional CNNs is available at:https://github.com/btgraham/SparseConvNet The world we live in is three dimensional, and time can also be thought of as an extra dimension, so there are a large number of possible applications for three and even four dimensional CNNs. Figure 1 shows what happens to sparse 3D data as it passes though a CNN. In this paper I apply CNNs to a variety of sparse 3D datasets.When applying CNNs to sparse data, it may be better to use small convolutional filters, as they do a better job of preserving sparsity in the computationally expensive lower layers of the network. To reduce the size of the filters, we have experimented with changing the underlying graph. See Figure 2. Figure 3 shows a variety of objects from the SHREC2015 Non-rigid 3D Shape Retrieval dataset, each stored as a mesh of triangles in the OFFfile format. The dataset contains 1200 exemplars split evenly between 50 classes (aliens, ants, armadillo, ...). The dataset was intended to be used for unsupervised learning, but as CNNs are most often used for supervised learning, we used 6-fold cross-validation to measure the ability of our 3D CNNs to learn shapes. To stop the dataset being too easy, we randomly rotated the objects during training and testing. This is to force the CNN to truly learn to recognize shape, and not rely on some classes of objects tending to have a certain orientation. We tested a variety of network architectures to explore the trade-off between speed and accuracy. Figure 4 shows an image from the Recognizing Human Actions video dataset. Taking differences between successive frame converts the dataset to a collection of sparse 2+1 dimensional objects. We also experimented with the more complicated UCF101 video dataset.[1] Ben G...

No abstract

No abstract

Technological advancements have made possible the emergence of Body Area Networks (BANs). There are numerous on-body channel characterizations in the literature performed on a phantom or a single human subject. In this paper, using multiple subjects, we consider the effect of body shape and gender on the on-body channel. A characterization of a narrowband on-body to on-body channel among different subjects is presented. The paper investigates the relationship between the propagation and the subject's physical characteristics. The investigation is performed at 2360 MHz; the new medical band undergoing FCC approval. Our results show that the path loss in women is less than that in men and the level of fade is usually higher in men than women. They also show that involuntary movements along with respiration cause small-scale fading that follows the Rice distribution

No abstract

Interest in on-body communication channels is growing as the use of wireless devices increases in medical, consumer and military sensor applications. This paper presents an experimental investigation and analysis of the narrowband on-body propagation channel. This analysis considers each of the factors affecting the channel during a range of stationary and motion activities in different environments with actual wireless mote devices on the body. Use of such motes allows greater freedom in the subject's movements and the inclusion of real-world indoor and outdoor environments in a test sequence. This paper identifies and analyses the effect of the different components of the signal propagation (mean propagation path gain, large-scale fading and small-scale fading) and the cause of the losses and variation due to activities, positions or environmental factors. Our results show the effect on the received signal and the impact of voluntary and involuntary movements, which cause shadowing effects. The analysis also allows us to identify sensor positions on the body that are more reliable and those positions that may require a relay or those that may be suitable for acting as a relay