Search Results for author:
Found 34 papers, 21 papers with code
ADV2E: Bridging the Gap Between Analogue Circuit and Discrete Frames in the Video-to-Events Simulator
We incorporate the analogue properties of event camera pixel circuits into the simulator design: (1) analogue filtering of signals from light intensity to events, and (2) a cutoff frequency that is independent of video frame rate.
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain.
Grand canonical generative diffusion model for crystalline phases and grain boundaries
The diffusion model has emerged as a powerful tool for generating atomic structures for materials science.
Sparse Prior Is Not All You Need: When Differential Directionality Meets Saliency Coherence for Infrared Small Target Detection
Infrared small target detection is crucial for the efficacy of infrared search and tracking systems.
Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution
As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important.
Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment
The Text Annotated Distortion, Appearance and Content (TADAC) database has over 1. 6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties.
Characterization of dim light response in DVS pixel: Discontinuity of event triggering time
Dynamic Vision Sensors (DVS) have recently generated great interest because of the advantages of wide dynamic range and low latency compared with conventional frame-based cameras.
Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.
LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields
Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields.
Spectroscopy-Guided Discovery of Three-Dimensional Structures of Disordered Materials with Diffusion Models
In this work, we introduce a new framework based on the diffusion model, a recent generative machine learning method to predict 3D structures of disordered materials from a target property.
Linear normalised hash function for clustering gene sequences and identifying reference sequences from multiple sequence alignments
The combination of MSA with the linear mapping hash function is a computationally efficient way of gene sequence clustering and can be a valuable tool for the assessment of similarity, clustering of different microbial genomes, identifying reference sequences, and for the study of evolution of bacteria and viruses.
Score dynamics: scaling molecular dynamics with picoseconds timestep via conditional diffusion model
Our current SD implementation is about two orders of magnitude faster than the MD counterpart for the systems studied in this work.
Learning dislocation dynamics mobility laws from large-scale MD simulations
The computational method of discrete dislocation dynamics (DDD), used as a coarse-grained model of true atomistic dynamics of lattice dislocations, has become of powerful tool to study metal plasticity arising from the collective behavior of dislocations.
SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World
In SpikingNeRF, each sampled point on the ray is matched to a particular time step and represented in a hybrid manner where the voxel grids are maintained as well.
Collaborative Auto-encoding for Blind Image Quality Assessment
Blind image quality assessment (BIQA) is a challenging problem with important real-world applications.
Revisiting Prototypical Network for Cross Domain Few-Shot Learning
Prototypical Network is a popular few-shot solver that aims at establishing a feature metric generalizable to novel few-shot classification (FSC) tasks using deep neural networks.
One-Stage Cascade Refinement Networks for Infrared Small Target Detection
Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection.
Score-based denoising for atomic structure identification
We propose an effective method for removing thermal vibrations that complicate the task of analyzing complex dynamics in atomistic simulation of condensed matter.
Aesthetically Relevant Image Captioning
Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS.
HDRfeat: A Feature-Rich Network for High Dynamic Range Image Reconstruction
A major challenge for high dynamic range (HDR) image reconstruction from multi-exposed low dynamic range (LDR) images, especially with dynamic scenes, is the extraction and merging of relevant contextual features in order to suppress any ghosting and blurring artifacts from moving objects.
Restoration of User Videos Shared on Social Media
This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms.
Accelerating discrete dislocation dynamics simulations with graph neural networks
Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials.
SurroundNet: Towards Effective Low-Light Image Enhancement
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance.
Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement
Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM).
VHS to HDTV Video Translation using Multi-task Adversarial Learning
In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model.
Attentional Local Contrast Networks for Infrared Small Target Detection
To mitigate the issue of minimal intrinsic features for pure data-driven methods, in this paper, we propose a novel model-driven deep network for infrared small target detection, which combines discriminative networks and conventional model-driven methods to make use of both labeled data and the domain knowledge.
Meta-Generating Deep Attentive Metric for Few-shot Classification
To mitigate this problem, we present a novel deep metric meta-generation method that turns to an orthogonal direction, ie, learning to adaptively generate a specific metric for a new FSL task based on the task description (eg, a few labelled samples).
Towards Disentangling Latent Space for Unsupervised Semantic Face Editing
In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing.
Asymmetric Contextual Modulation for Infrared Small Target Detection
Single-frame infrared small target detection remains a challenge not only due to the scarcity of intrinsic target characteristics but also because of lacking a public dataset.
Tricritical physics in two-dimensional $p$-wave superfluids
When strong quantum fluctuations near resonance are taken into account, the line of continuous phase transitions terminates at two multicritical points near resonance, between which the transitions are expected to be first-order ones.
Quantum Gases
Spectral Regularization for Combating Mode Collapse in GANs
Theoretical analysis shows that the optimal solution to the discriminator has a strong relationship to the spectral distributions of the weight matrix. Therefore, we monitor the spectral distribution in the discriminator of spectral normalized GANs (SN-GANs), and discover a phenomenon which we refer to as spectral collapse, where a large number of singular values of the weight matrices drop dramatically when mode collapse occurs.
Semi-parametric Bayesian variable selection for gene-environment interactions
Existing Bayesian methods for G$\times$E interaction studies are challenged by the high-dimensional nature of the study and the complexity of environmental influences.
Methodology
Compressive sensing lattice dynamics. I. General formalism
{\it Ab initio\/} calculations have been successfully used for evaluating lattice dynamical properties of solids within the (quasi-)harmonic approximation (i. e., assuming non-interacting phonons with infinite lifetimes), but it remains difficult to treat anharmonicity in all but the simplest compounds.
Computational Physics Materials Science
Compressive sensing lattice dynamics. II. Efficient phonon calculations and long-range interactions
We apply the compressive sensing lattice dynamics (CSLD) method to calculate phonon dispersion for crystalline solids.
Materials Science
