Related papers: Automated rendering of multi-stranded DNA complexe…
Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…
High-content screening uses large collections of unlabeled cell image data to reason about genetics or cell biology. Two important tasks are to identify those cells which bear interesting phenotypes, and to identify sub-populations enriched…
Purpose: An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T2 mapping from single-shot OverLapping-Echo Detachment (OLED) planar imaging. Methods:…
Recent work has highlighted the advantage of jointly learning grounded sentence representations from multiple languages. However, the data used in these studies has been limited to an aligned scenario: the same images annotated with…
Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources,…
A key challenge in cancer immunotherapy biomarker research is quantification of pattern changes in microscopic whole slide images of tumor biopsies. Different cell types tend to migrate into various tissue compartments and form variable…
To be able to predict a molecular graph structure ($W$) given a 2D image of a chemical compound ($U$) is a challenging problem in machine learning. We are interested to learn $f: U \rightarrow W$ where we have a fully mediating…
Recent advances in differentiable rendering, which allow calculating the gradients of 2D pixel values with respect to 3D object models, can be applied to estimation of the model parameters by gradient-based optimization with only 2D…
In this dissertation we report results of our research on dense distributed representations of text data. We propose two novel neural models for learning such representations. The first model learns representations at the document level,…
A pseudoline is a homeomorphic image of the real line in the plane so that its complement is disconnected. An arrangement of pseudolines is a set of pseudolines in which every two cross exactly once. A drawing of a graph is pseudolinear if…
In this work, we propose a deep learning approach for parallel magnetic resonance imaging (MRI) reconstruction, termed a variable splitting network (VS-Net), for an efficient, high-quality reconstruction of undersampled multi-coil MR data.…
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…
We present an algorithm which computes a planar 2-spanner from an Unit Disk Graph when the node density is sufficient. The communication complexity in terms of number of node's identifier sent by the algorithm is $6n$, while the…
Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural network to approximate complex shapes with implicit…
Extracting structured subgraphs inside large graphs - often known as the planted subgraph problem - is a fundamental question that arises in a range of application domains. This problem is NP-hard in general, and as a result, significant…
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…
In this paper, we present an optical computing method for string data alignment applicable to genome information analysis. By applying moire technique to spatial encoding patterns of deoxyribonucleic acid (DNA) sequences, association…
We propose a neural network-based real-time volume rendering method for realistic and efficient rendering of volumetric media. The traditional volume rendering method uses path tracing to solve the radiation transfer equation, which…
We proposed a probabilistic algorithm to solve the Multiple Sequence Alignment problem. The algorithm is a Simulated Annealing (SA) that exploits the representation of the Multiple Alignment between $D$ sequences as a directed polymer in…
Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health. To allow for proper risk assessment, a precise and statistically relevant…