Related papers: A Full Rank Pileup Deconvolution Scheme Suitable f…

Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by…

Benchmarking anomaly detection approaches for multivariate time series is a challenging task due to a lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders…

Estimating Plume Cloud (PC) height is essential for various applications, such as global climate models. Smokestack Plume Rise (PR) is the constant height at which the PC is carried downwind as its momentum dissipates and the PC and the…

Object detection generally requires sliding-window classifiers in tradition or anchor box based predictions in modern deep learning approaches. However, either of these approaches requires tedious configurations in boxes. In this paper, we…

Multi-stage cascade architecture exists widely in many industrial systems such as recommender systems and online advertising, which often consists of sequential modules including matching, pre-ranking, ranking, etc. For a long time, it is…

The study of astronomical phenomena through ground-based observations is always challenged by the distorting effects of Earth's atmosphere. Traditional methods of post-facto image correction, essential for correcting these distortions,…

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited…

Blind deconvolution is the problem of recovering a sharp image and a blur kernel from a noisy blurry image. Recently, there has been a significant effort on understanding the basic mechanisms to solve blind deconvolution. While this effort…

A detailed Monte-Carlo code has been developed from basic principles that simulates almost all of the basic photon and charged particle interactions. The code is used to derive the response functions of a high energy photon detector to…

Fourier phase retrieval is a classical problem of restoring a signal only from the measured magnitude of its Fourier transform. Although Fienup-type algorithms, which use prior knowledge in both spatial and Fourier domains, have been widely…

Linear classifiers with random convolution kernels are computationally efficient methods that need no design or domain knowledge. Unlike deep neural networks, there is no need to hand-craft a network architecture; the kernels are randomly…

We propose DiscoverDCP, a data-driven framework that integrates symbolic regression with the rule sets of Disciplined Convex Programming (DCP) to perform system identification. By enforcing that all discovered candidate model expressions…

To better understand the energy response of the Antineutrino Detector (AD), the Daya Bay Reactor Neutrino Experiment installed a full Flash ADC readout system on one AD that allowed for simultaneous data taking with the current readout…

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic {\em unpooling} is employed to link consecutive layers in the model, yielding…

Probabilistic relational models such as parametric factor graphs enable efficient (lifted) inference by exploiting the indistinguishability of objects. In lifted inference, a representative of indistinguishable objects is used for…

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…

The CTC model has been widely applied to many application scenarios because of its simple structure, excellent performance, and fast inference speed. There are many peaks in the probability distribution predicted by the CTC models, and each…

Clustering algorithms are of fundamental importance when dealing with large unstructured datasets and discovering new patterns and correlations therein, with applications ranging from scientific research to medical imaging and marketing…

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance…

A deep learning method for the particle trajectory reconstruction with the DAMPE experiment is presented. The developed algorithms constitute the first fully machine-learned track reconstruction pipeline for space astroparticle missions.…