Related papers: MOSES: A Streaming Algorithm for Linear Dimensiona…
The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…
Video Object Segmentation (VOS) is typically formulated in a semi-supervised setting. Given the ground-truth segmentation mask on the first frame, the task of VOS is to track and segment the single or multiple objects of interests in the…
The paper presents a strategy to construct an incremental Singular Value Decomposition (SVD) for time-evolving, spatially 3D discrete data sets. A low memory access procedure for reducing and deploying the snapshot data is presented.…
Motivated by machine learning applications in networks of sensors, internet-of-things (IoT) devices, and autonomous agents, we propose techniques for distributed stochastic convex learning from high-rate data streams. The setup involves a…
Modeling and predicting the dynamics of complex multiscale systems remains a significant challenge due to their inherent nonlinearities and sensitivity to initial conditions, as well as limitations of traditional machine learning methods…
In bandwidth-limited online video streaming, videos are usually downsampled and compressed. Although recent online video super-resolution (online VSR) approaches achieve promising results, they are still compute-intensive and fall short of…
Reduced-order models (ROMs) can accelerate high-dimensional dynamical simulations, but their accuracy often deteriorates when online dynamics leave the regime represented by offline training data. We develop a projection-based adaptive ROM…
Scale-resolving flow simulations often feature several million [thousand] spatial [temporal] discrete degrees of freedom. When storing or re-using these data, e.g., to subsequently train some sort of data-based surrogate or compute…
A new method is proposed to decrease the transmission delay of visual and non-visual medical records by using edge computing and Dynamic Vision Sensing (DVS) technologies. The simulation results show that the proposed scheme can decrease…
Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment the current frame via softmax attention. However, STM…
Molecular dynamics (MD) simulations have been widely applied to study macromolecules including proteins. However, high-dimensionality of the datasets produced by simulations makes it difficult for thorough analysis, and further hinders a…
Autonomous systems, such as self-driving cars, rely on reliable semantic environment perception for decision making. Despite great advances in video semantic segmentation, existing approaches ignore important inductive biases and lack…
We consider a streaming data model in which n sensors observe individual streams of data, presented in a turnstile model. Our goal is to analyze the singular value decomposition (SVD) of the matrix of data defined implicitly by the stream…
Current prevailing Video Object Segmentation methods follow the pipeline of extraction-then-matching, which first extracts features on current and reference frames independently, and then performs dense matching between them. This decoupled…
Subsampling is a widely used and effective approach for addressing the computational challenges posed by massive datasets. Substantial progress has been made in developing non-uniform, probability-based subsampling schemes that prioritize…
Compressive sensing (CS) reconstructs images from sub-Nyquist measurements by solving a sparsity-regularized inverse problem. Traditional CS solvers use iterative optimizers with hand crafted sparsifiers, while early data-driven methods…
Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle,…
High-dimensional classification has become an increasingly important problem. In this paper we propose a "Multivariate Adaptive Stochastic Search" (MASS) approach which first reduces the dimension of the data space and then applies a…
Spectral embedding based on the Singular Value Decomposition (SVD) is a widely used "preprocessing" step in many learning tasks, typically leading to dimensionality reduction by projecting onto a number of dominant singular vectors and…
Linear subspace models are pervasive in computational sciences and particularly used for large datasets which are often incomplete due to privacy issues or sampling constraints. Therefore, a critical problem is developing an efficient…