There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

CA : A Cancer Journal for Clinicians

Introduction to linear and nonlinear programming

Bilateral teleoperation: An historical survey

Local Interaction Models for Haptic Rendering of Rigid Environments

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task. Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network. A natural advantage of our design lies in the exploration of view-to-view relationships using self-attention among multiple unordered inputs. On ShapeNet - a large-scale 3D reconstruction benchmark dataset, our method achieves a new state-of-the-art accuracy in multi-view reconstruction with fewer parameters ($70\%$ less) than other CNN-based methods. Experimental results also suggest the strong scaling capability of our method. Our code will be made publicly available.

/pdf/multi-view-3d-reconstruction-with-transformer-513qrtbi2b.pdf

Multi-view 3D Reconstruction with Transformer

An Indirect Adaptive Regulator: Computational Algorithms and Simulation Results

Delineation of the perimeter of hollow structures, such as veins and arteries, from ultrasound images is an important step in US-based medical interventions. A simple and efficient approach is proposed for edge detection in ultrasound images. The technique examines the radial edge profiles for ”unit root” based on the Dickey-Fuller test. The existence of the unit root is a sign of a trend, and hence non-stationarity, in the statistics of the edge profile. The method is applied to simulated data and clinical images of human arteries and veins. The outcomes are validated based on the average of the Hausdorff distance between the automatically derived vessel contours and vessel contours marked by five experts. The proposed edge detection method provides accurate segmentations (average Hausdorff distance from expert segmentation of 1.5 mm in vessel images and 0.4 mm in simulated data).

Preliminary results of an ultrasound segmentation method based on statistical unit-root test of B-scan radial intensity profiles

A novel input-output device utilizing force feedback has been developed for use in everyday point-and-pick functions. Compared with a previous prototype, the significant improvements in motion range were made. The integration of a dedicated microcontroller subsystem with a Macintosh host is presented. An outline of a new haptographical user interface is given. Initial selection time comparisons between the force feedback device and a regular mouse are provided.

Septimiu E. Salcudean

Papers

Local Interaction Models for Haptic Rendering of Rigid Environments

Multi-view 3D Reconstruction with Transformer

An Indirect Adaptive Regulator: Computational Algorithms and Simulation Results

Preliminary results of an ultrasound segmentation method based on statistical unit-root test of B-scan radial intensity profiles

An integrated haptographical user interface using a force feedback mouse