Search Results for author:
Found 114 papers, 18 papers with code
Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation
A novel model, called Adaptive Computationally Efficient (ACE) network, is proposed, which takes advantage of a Gaussian kernel based Gate Module to dynamically switch the computation between a light model and a heavy network for feature extraction.
Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems
The recommendation with a cache is a solution to this problem, where a user-wise result cache is used to provide recommendations when the recommender system cannot afford a real-time computation.
Neural Network Approach for Non-Markovian Dissipative Dynamics of Many-Body Open Quantum Systems
Simulating the dynamics of open quantum systems coupled to non-Markovian environments remains an outstanding challenge due to exponentially scaling computational costs.
One-Click Upgrade from 2D to 3D: Sandwiched RGB-D Video Compression for Stereoscopic Teleconferencing
In this paper, we propose a new approach to upgrade a 2D video codec to support stereo RGB-D video compression, by wrapping it with a neural pre- and post-processor pair.
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues
SPSC and SDSC augment live samples into simulated attack samples by simulating spoofing clues of physical and digital attacks, respectively, which significantly improve the capability of the model to detect "unseen" attack types.
DiffGaze: A Diffusion Model for Continuous Gaze Sequence Generation on 360° Images
We present DiffGaze, a novel method for generating realistic and diverse continuous human gaze sequences on 360{\deg} images based on a conditional score-based denoising diffusion model.
Interactive $360^{\circ}$ Video Streaming Using FoV-Adaptive Coding with Temporal Prediction
We develop a low-latency FoV-adaptive coding and streaming system for interactive applications that is robust to bandwidth variations and FoV prediction errors.
DeepEMC-T2 Mapping: Deep Learning-Enabled T2 Mapping Based on Echo Modulation Curve Modeling
The modified U-Net employs several new features to improve the accuracy of T2/PD estimation.
Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent
This paper considers the problem of recovering a tensor with an underlying low-tubal-rank structure from a small number of corrupted linear measurements.
UNEX-RL: Reinforcing Long-Term Rewards in Multi-Stage Recommender Systems with UNidirectional EXecution
In recent years, there has been a growing interest in utilizing reinforcement learning (RL) to optimize long-term rewards in recommender systems.
Multi-agent Reinforcement Learning
Recommendation Systems
+2
5G Edge Vision: Wearable Assistive Technology for People with Blindness and Low Vision
In an increasingly visual world, people with blindness and low vision (pBLV) face substantial challenges in navigating their surroundings and interpreting visual information.
Efficient Generalized Low-Rank Tensor Contextual Bandits
In this paper, we aim to build a novel bandits algorithm that is capable of fully harnessing the power of multi-dimensional data and the inherent non-linearity of reward functions to provide high-usable and accountable decision-making services.
VisPercep: A Vision-Language Approach to Enhance Visual Perception for People with Blindness and Low Vision
By combining the prompt and input image, a large vision-language model (i. e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt.
Lifting the Veil: Unlocking the Power of Depth in Q-learning
In this paper, we make fundamental contributions to the field of reinforcement learning by answering to the following three questions: Why does deep Q-learning perform so well?
Distillation Improves Visual Place Recognition for Low-Quality Queries
The shift to online computing for real-time visual localization often requires streaming query images/videos to a server for visual place recognition (VPR), where fast video transmission may result in reduced resolution or increased quantization.
Provable Tensor Completion with Graph Information
For the model, we establish a rigorous mathematical representation of the dynamic graph, based on which we derive a new tensor-oriented graph smoothness regularization.
Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning
Nonlocal self-similarity within natural images has become an increasingly popular prior in deep-learning models.
Ranked #5 on
Grayscale Image Denoising
on BSD68 sigma50
Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameters
Furthermore, we introduce an inverted kinematic(IK) network to translate the estimated hand mesh to a biomechanically feasible set of joint rotation parameters, which is necessary for applications that leverage pose estimation for controlling robotic hands.
Deep learning reveals the common spectrum underlying multiple brain disorders in youth and elders from brain functional networks
Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions.
Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes
The novelties of our research are as follows: 1) From a methodological perspective, we present a novel and scalable approach for generating DTRs by combining distributed learning with Q-learning.
Dual-mode adaptive-SVD ghost imaging
In this paper, we present a dual-mode adaptive singular value decomposition ghost imaging (A-SVD GI), which can be easily switched between the modes of imaging and edge detection.
Efficient Fraud Detection Using Deep Boosting Decision Trees
In this paper, we propose deep boosting decision trees (DBDT), a novel approach for fraud detection based on gradient boosting and neural networks.
Learning Neural Volumetric Field for Point Cloud Geometry Compression
The neural field representation of the point cloud includes the network parameters and all the latent codes, which are generated by using back-propagation over the network parameters and its input.
Deterioration Prediction using Time-Series of Three Vital Signs and Current Clinical Features Amongst COVID-19 Patients
This is infeasible for telehealth solutions and highlights a gap in deterioration prediction models that are based on minimal data, which can be recorded at a large scale in any clinic, nursing home, or even at the patient's home.
Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance
We further assess the impact of the distance of an object to the camera on the detection accuracy and show that higher spatial resolution enables a greater detection range.
Learning to Predict on Octree for Scalable Point Cloud Geometry Coding
Octree-based point cloud representation and compression have been adopted by the MPEG G-PCC standard.
Improved Image Classification with Token Fusion
In this paper, we propose a method using the fusion of CNN and transformer structure to improve image classification performance.
Detect and Approach: Close-Range Navigation Support for People with Blindness and Low Vision
These functions enable the system to suggest an initial navigation path, continuously update the path as the user moves, and offer timely recommendation about the correction of the user's path.
Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior
Gabor-like filters have been observed in the early layers of CNN classifiers and even throughout low-level image processing networks.
Feature Compression for Rate Constrained Object Detection on the Edge
In this work, we consider a "split computation" system to offload a part of the computation of the YOLO object detection model.
FS6D: Few-Shot 6D Pose Estimation of Novel Objects
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models.
Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis
These models hence are not optimized for dialog-level emotion detection, i. e. to predict the emotion category of a dialog as a whole.
Exact Decomposition of Joint Low Rankness and Local Smoothness Plus Sparse Matrices
It is known that the decomposition in low-rank and sparse matrices (\textbf{L+S} for short) can be achieved by several Robust PCA techniques.
Network-Aware 5G Edge Computing for Object Detection: Augmenting Wearables to "See" More, Farther and Faster
The vision evaluation is combined with a detailed full-stack wireless network simulation to determine the distribution of throughputs and delays with real navigation paths and ray-tracing from new high-resolution 3D models in an urban environment.
DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning
Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge.
An original model for multi-target learning of logical rules for knowledge graph reasoning
In this paper, we study the problem of learning logical rules for reasoning on knowledge graphs for completing missing factual triplets.
Scanpath Prediction on Information Visualisations
We propose Unified Model of Saliency and Scanpaths (UMSS) -- a model that learns to predict visual saliency and scanpaths (i. e. sequences of eye fixations) on information visualisations.
CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing
In this work, we propose an unrolled convolutional dictionary learning network (CDLNet) and demonstrate its competitive denoising and joint denoising and demosaicing (JDD) performance both in low and high parameter count regimes.
Domain Adaptation of Networks for Camera Pose Estimation: Learning Camera Pose Estimation Without Pose Labels
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities.
Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets
In this paper, we study the generalization performance of global minima for implementing empirical risk minimization (ERM) on over-parameterized deep ReLU nets.
Nyström Regularization for Time Series Forecasting
This paper focuses on learning rate analysis of Nystr\"{o}m regularization with sequential sub-sampling for $\tau$-mixing time series.
An Improved Frequent Directions Algorithm for Low-Rank Approximation via Block Krylov Iteration
Frequent Directions, as a deterministic matrix sketching technique, has been proposed for tackling low-rank approximation problems.
Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Accordingly, a novel formulation for tensor completion and an effective optimization algorithm, called as tensor completion by parallel weighted matrix factorization via tensor train (TWMac-TT), is proposed.
Effective Streaming Low-tubal-rank Tensor Approximation via Frequent Directions
Low-tubal-rank tensor approximation has been proposed to analyze large-scale and multi-dimensional data.
End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation
We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction.
Double-Dot Network for Antipodal Grasp Detection
This paper proposes a new deep learning approach to antipodal grasp detection, named Double-Dot Network (DD-Net).
Universal Consistency of Deep Convolutional Neural Networks
Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind.
Effective Snapshot Compressive-Spectral Imaging via Deep Denoising and Total Variation Priors
Specifically, we propose an optimization objective to utilize these two priors.
A method using deep learning to discover new predictors of CRT response from mechanical dyssynchrony on gated SPECT MPI
Correlation analysis was used to explain the relationships between new parameters with conventional LVMD parameters.
PDWN: Pyramid Deformable Warping Network for Video Interpolation
At the finest scale, the two warped frames are adaptively blended to generate the middle frame.
CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning
In addition, we leverage the model's interpretable construction to propose an augmentation of the network's thresholds that enables state-of-the-art blind denoising performance and near-perfect generalization on noise-levels unseen during training.
Ranked #9 on
Grayscale Image Denoising
on BSD68 sigma25
The distance between the weights of the neural network is meaningful
In the application of neural networks, we need to select a suitable model based on the problem complexity and the dataset scale.
Frequency Regularized Deep Convolutional Dictionary Learning and Application to Blind Denoising
Sparse representation via a learned dictionary is a powerful prior for natural images.
Motion Adaptive Pose Estimation From Compressed Videos
A novel model, called Motion Adaptive Pose Net is proposed to exploit the compressed streams to efficiently decode pose sequences from videos.
Incoherent transport in a classical spin liquid
The finite zero temperature limits of the diffusion constants are then naturally understood as a result of the finite mean free path of the normal modes due to the effective disorder.
Strongly Correlated Electrons Statistical Mechanics
Marcus' electron transfer rate revisited via a Rice-Ramsperger-Kassel-Marcus analogue: A unified formalism for linear and nonlinear solvation scenarios
In this work, on the basis of the thermodynamic solvation potentials analysis, we reexamine Marcus' formula with respect to the Rice-Ramsperger-Kassel-Marcus (RRKM) theory.
Chemical Physics
Kernel-based L_2-Boosting with Structure Constraints
Numerically, we carry out a series of simulations to show the promising performance of KReBooT in terms of its good generalization, near over-fitting resistance and structure constraints.
Theoretical formulations on thermodynamics of quantum impurity systems
In this work, we put forward the theoretical foundation toward thermodynamics of quantum impurity systems measurable in experiments.
Quantum Physics Statistical Mechanics
Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model
Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H. 264/AVC and H. 265/HEVC.
Learning Scalable Multi-Agent Coordination by Spatial Differentiation for Traffic Signal Control
By extending the idea of Markov Chain to the dimension of space-time, this truly decentralized coordination mechanism replaces the graph attention method and realizes the decoupling of the road network, which is more scalable and more in line with practice.
Deep Mouse: An End-to-end Auto-context Refinement Framework for Brain Ventricle and Body Segmentation in Embryonic Mice Ultrasound Volumes
High-frequency ultrasound (HFU) is well suited for imaging embryonic mice due to its noninvasive and real-time characteristics.
A preference learning framework for multiple criteria sorting with diverse additive value models and valued assignment examples
We propose an optimization model for constructing a preference model from such valued examples by maximizing the credible consistency among reference alternatives.
Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling
This paper proposes a novel Non-Local Attention optmization and Improved Context modeling-based image compression (NLAIC) algorithm, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure.
Automatic Mouse Embryo Brain Ventricle & Body Segmentation and Mutant Classification From Ultrasound Data Using Deep Learning
High-frequency ultrasound (HFU) is well suited for imaging embryonic mice in vivo because it is non-invasive and real-time.
Masked-RPCA: Sparse and Low-rank Decomposition Under Overlaying Model and Application to Moving Object Detection
Robust Principal Component Analysis (RPCA) performs low-rank and sparse decomposition and accomplishes such a task when the background is stationary and the foreground is dynamic and relatively small.
A Method to Learn Embedding of a Probabilistic Medical Knowledge Graph: Algorithm Development
This paper proposes an algorithm named as PrTransH to learn embedding vectors from real world EMR data based medical knowledge.
Identification of relevant diffusion MRI metrics impacting cognitive functions using a novel feature selection method
Mild Traumatic Brain Injury (mTBI) is a significant public health problem.
Deep Plug-and-play Prior for Low-rank Tensor Completion
By integrating deterministic low-rankness prior to the data-driven deep prior, we suggest a novel regularized tensor completion model for multi-dimensional image completion.
Non-local Attention Optimized Deep Image Compression
This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure.
TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis
We propose a novel network structure named trackNet that can directly detect a 3D tube enclosing a moving object in a video segment by extending the faster R-CNN framework.
Very Long Term Field of View Prediction for 360-degree Video Streaming
In this work, we treat the FoV prediction as a sequence learning problem, and propose to predict the target user's future FoV not only based on the user's own past FoV center trajectory but also other users' future FoV locations.
Deep Generative Learning via Variational Gradient Flow
We propose a general framework to learn deep generative models via \textbf{V}ariational \textbf{Gr}adient Fl\textbf{ow} (VGrow) on probability spaces.
Reconstructing Speech Stimuli From Human Auditory Cortex Activity Using a WaveNet Approach
The superior temporal gyrus (STG) region of cortex critically contributes to speech recognition.
Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic Mice
Volumetric analysis of brain ventricle (BV) structure is a key tool in the study of central nervous system development in embryonic mice.
Brain Ventricle Localization And Segmentation In 3D Ultrasound Images
Segmentation
Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing
The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks.
Integrated Server for Measurement-Device-Independent Quantum Key Distribution Network
Quantum key distribution (QKD), harnessing quantum physics and optoelectronics, may promise unconditionally secure information exchange in theory.
Quantum Physics
MTBI Identification From Diffusion MR Images Using Bag of Adversarial Visual Features
Unlike most of previous works, which use hand-crafted features extracted from different parts of brain for MTBI classification, we employ feature learning algorithms to learn more discriminative representation for this task.
Multispectral Image Intrinsic Decomposition via Subspace Constraint
In this paper, a new Multispectral Image Intrinsic Decomposition model (MIID) is presented to decompose the shading and reflectance from a single multispectral image.
FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors
In this paper, we propose a novel video rain streak removal approach FastDeRain, which fully considers the discriminative characteristics of rain streaks and the clean video in the gradient domain.
Multispectral Image Intrinsic Decomposition via Low Rank Constraint
In this paper, a Low Rank Multispectral Image Intrinsic Decomposition model (LRIID) is presented to decompose the shading and reflectance from a single multispectral image.
A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI
Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1. 7 million people annually in US.
Pixel-wise object tracking
In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background.
Identifying Mild Traumatic Brain Injury Patients From MR Images Using Bag of Visual Words
Mild traumatic brain injury (mTBI) is a growing public health problem with an estimated incidence of one million people annually in US.
Tensor RPCA by Bayesian CP Factorization With Complex Noise
In this paper, we propose a tensor RPCA model based on CP decomposition and model data noise by Mixture of Gaussians (MoG).
A Machine Learning Approach For Identifying Patients with Mild Traumatic Brain Injury Using Diffusion MRI Modeling
While diffusion MRI has been extremely promising in the study of MTBI, identifying patients with recent MTBI remains a challenge.
Hyperspectral Image Restoration via Total Variation Regularized Low-rank Tensor Decomposition
In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part respectively.
A Novel Tensor-Based Video Rain Streaks Removal Approach via Utilizing Discriminatively Intrinsic Priors
Rain streaks removal is an important issue of the outdoor vision system and has been recently investigated extensively.
SPLBoost: An Improved Robust Boosting Algorithm Based on Self-paced Learning
Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers.
Text Extraction From Texture Images Using Masked Signal Decomposition
Text extraction is an important problem in image processing with applications from optical character recognition to autonomous driving.
Segmentation of 3D High-frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut with Energy Functional Adapted to Local Intensity Distribution
In high-frequency ultrasound images of lymph nodes, the intensity distribution of lymph node parenchyma and fat varies spatially because of acoustic attenuation and focusing effects.
A General Model for Robust Tensor Factorization with Unknown Noise
We provide two versions of the algorithm with different tensor factorization operations, i. e., CP factorization and Tucker factorization.
Multi Resolution LSTM For Long Term Prediction In Neural Activity Video
Epileptic seizures are caused by abnormal, overly syn- chronized, electrical activity in the brain.
An ADMM Approach to Masked Signal Decomposition Using Subspace Representation
Signal decomposition is a classical problem in signal processing, which aims to separate an observed signal into two or more components each with its own property.
Subspace Learning in The Presence of Sparse Structured Outliers and Noise
Subspace learning is an important problem, which has many applications in image and video processing.
An Experimental Study of Deep Convolutional Features For Iris Recognition
Different features have been used to perform iris recognition in the past.
Image Segmentation Using Overlapping Group Sparsity
Sparse decomposition has been widely used for different applications, such as source separation, image classification and image denoising.
Diversity encouraged learning of unsupervised LSTM ensemble for neural activity video prediction
Recog- nizing that there exist multiple activity pattern clusters, we have further explored to train an ensemble of LSTM mod- els so that each model can specialize in modeling certain neural activities, without explicitly clustering the training data.
Image Decomposition Using a Robust Regression Approach
This paper considers how to separate text and/or graphics from smooth background in screen content and mixed content images and proposes an algorithm to perform this segmentation task.
Face Recognition Using Scattering Convolutional Network
Face recognition has been an active research area in the past few decades.
Screen Content Image Segmentation Using Robust Regression and Sparse Decomposition
This paper considers how to separate text and/or graphics from smooth background in screen content and mixed document images and proposes two approaches to perform this segmentation task.
Robust Tensor Factorization With Unknown Noise
However, real data are often corrupted by noise with an unknown distribution.
Palmprint Recognition Using Deep Scattering Convolutional Network
Many algorithms have been proposed for palmprint recognition in the past, majority of them being based on features extracted from the transform domain.
Screen Content Image Segmentation Using Sparse Decomposition and Total Variation Minimization
Sparse decomposition has been widely used for different applications, such as source separation, image classification, image denoising and more.
Super-resolution reconstruction of hyperspectral images via low rank tensor modeling and total variation regularization
In this paper, we propose a novel approach to hyperspectral image super-resolution by modeling the global spatial-and-spectral correlation and local smoothness properties over hyperspectral images.
Divide and Conquer Local Average Regression
After theoretically analyzing the pros and cons, we find that although the divide and conquer local average regression can reach the optimal learning rate, the restric- tion to the number of data blocks is a bit strong, which makes it only feasible for small number of data blocks.
A Novel Sparsity Measure for Tensor Recovery
In this paper, we propose a new sparsity regularizer for measuring the low-rank structure underneath a tensor.
Screen Content Image Segmentation Using Sparse-Smooth Decomposition
In this paper, sparse decomposition is used for image segmentation.
Fingerprint Recognition Using Translation Invariant Scattering Network
Different features and algorithms have been used for fingerprint recognition in the past.
Iris Recognition Using Scattering Transform and Textural Features
Iris recognition has drawn a lot of attention since the mid-twentieth century.
Shrinkage degree in $L_2$-re-scale boosting for regression
Re-scale boosting (RBoosting) is a variant of boosting which can essentially improve the generalization performance of boosting learning.
Re-scale boosting for regression and classification
Boosting is a learning scheme that combines weak prediction rules to produce a strong composite estimator, with the underlying intuition that one can obtain accurate prediction rules by combining "rough" ones.
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.
Screen Content Image Segmentation Using Least Absolute Deviation Fitting
The proposed method is designed based on the assumption that the background part of the image is smoothly varying and can be represented by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity and cannot be modeled by this smooth representation.
A Robust Regression Approach for Background/Foreground Segmentation
Background/foreground segmentation has a lot of applications in image and video processing.
