Search Results for author:
Found 295 papers, 108 papers with code
DETRs Beat YOLOs on Real-time Object Detection
Our RT-DETR-R50 / R101 achieves 53. 1% / 54. 3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy.
Ranked #5 on
Real-Time Object Detection
on MS COCO
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.
Ranked #4 on
Dynamic Link Prediction
on DBLP Temporal
FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation
In this paper, motivated by object-oriented programming, we model the subject as a derived class whose base class is its semantic category.
CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks
In addition to its large scale, CodeNet has a rich set of high-quality annotations to benchmark and help accelerate research in AI techniques for a variety of critical coding tasks, including code similarity and classification, code translation between a large variety of programming languages, and code performance (runtime and memory) improvement techniques.
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series
Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks.
Ranked #3 on
Anomaly Detection
on voraus-AD
The 1st Tiny Object Detection Challenge:Methods and Results
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications
To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning.
Ranked #3 on
Node Classification
on Citeseer Full-supervised
Attention on Attention for Image Captioning
In this paper, we propose an Attention on Attention (AoA) module, which extends the conventional attention mechanisms to determine the relevance between attention results and queries.
DAG-GNN: DAG Structure Learning with Graph Neural Networks
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.
Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution
Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system.
Scalable Graph Learning for Anti-Money Laundering: A First Look
Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150, 000 people since 2006, upwards of 700, 000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people.
Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints.
Discrete Graph Structure Learning for Forecasting Multiple Time Series
Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model.
Weighted Sum-Rate Maximization for Reconfigurable Intelligent Surface Aided Wireless Networks
Our objective is to maximize the weighted sum-rate (WSR) of all users by joint designing the beamforming at the access point (AP) and the phase vector of the RIS elements, while both the perfect channel state information (CSI) setup and the imperfect CSI setup are investigated.
Signal Processing
Weighted Sum-Rate Optimization for Intelligent Reflecting Surface Enhanced Wireless Networks
In addition, we consider a practical IRS assumption, in which the passive elements can only shift the incident signal to discrete phase levels.
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality.
DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information.
Directed Acyclic Graph Neural Networks
Graph-structured data ubiquitously appears in science and engineering.
Ranked #8 on
Graph Property Prediction
on ogbg-code2
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Most video-and-language representation learning approaches employ contrastive learning, e. g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs.
Ranked #2 on
Video Retrieval
on LSMDC
(text-to-video Mean Rank metric)
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i. e., p(candidates|query).
Ranked #15 on
Video Retrieval
on MSVD
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Contrastive learning-based video-language representation learning approaches, e. g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs.
Ranked #8 on
Video Question Answering
on MSRVTT-QA
Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment
In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings.
Learning Representation for Clustering via Prototype Scattering and Positive Sampling
The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness.
Ranked #2 on
Image Clustering
on ImageNet-10
Data-Efficient Graph Grammar Learning for Molecular Generation
This is a non-trivial task for neural network-based generative models since the relevant chemical knowledge can only be extracted and generalized from the limited training data.
A Unified Pyramid Recurrent Network for Video Frame Interpolation
Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis.
Ranked #2 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(PSNR metric)
Integration of Physics-Based and Data-Driven Models for Hyperspectral Image Unmixing
Spectral unmixing is one of the most important quantitative analysis tasks in hyperspectral data processing.
Locality Guidance for Improving Vision Transformers on Tiny Datasets
Therefore, our locality guidance approach is very simple and efficient, and can serve as a basic performance enhancement method for VTs on tiny datasets.
SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
By stacking RUs in a deep-to-shallow manner, SRN exploits the 'flow' of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales.
SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond
The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages.
Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning
The complex relationships between operations and machines are represented precisely and concisely, for which a dual-attention network (DAN) comprising several interconnected operation message attention blocks and machine message attention blocks is proposed.
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short.
Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification
In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.
RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data
In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsource data.
Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning
Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension.
Hyperspectral Image Super-Resolution
Hyperspectral Unmixing
+1
Adaptively Aligned Image Captioning via Adaptive Attention Time
In this paper, we propose a novel attention model, namely Adaptive Attention Time (AAT), to align the source and the target adaptively for image captioning.
Annotation-efficient deep learning for automatic medical image segmentation
Automatic medical image segmentation plays a critical role in scientific research and medical care.
Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension.
Online Planner Selection with Graph Neural Networks and Adaptive Scheduling
Automated planning is one of the foundational areas of AI.
IPC: A Benchmark Data Set for Learning with Graph-Structured Data
Benchmark data sets are an indispensable ingredient of the evaluation of graph-based machine learning methods.
Ranked #2 on
Graph Classification
on IPC-lifted
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
Both the coarsening matrix and the transport cost matrix are parameterized, so that an optimal coarsening strategy can be learned and tailored for a given set of graphs.
Cooperative Pursuit with Multi-Pursuer and One Faster Free-moving Evader
When the faster evader is allowed to move freely without any constraint, the main issues are how to form an encirclement to trap the evader into the capture domain, how to balance between forming an encirclement and approaching the faster evader, and what conditions make the capture possible.
Systems and Control Systems and Control
Training-free Transformer Architecture Search
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.
CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
For the task of end-to-end scene text recognition, our method outperforms Mask TextSpotter v3 by 1. 1% on Total-Text.
Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery.
Enhanced Bi-directional Motion Estimation for Video Frame Interpolation
We present a novel simple yet effective algorithm for motion-based video frame interpolation.
Ranked #3 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(LPIPS metric)
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
To tackle the LLM hallucination, three key questions should be well studied: how to detect hallucinations (detection), why do LLMs hallucinate (source), and what can be done to mitigate them (mitigation).
Image-based Virtual Fitting Room
We firstly used Mask R-CNN to find the regions of different fashion items, and secondly used Neural Style Transfer to change the style of the selected fashion items.
Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency.
CDNet: Centripetal Direction Network for Nuclear Instance Segmentation
Specifically, we define the centripetal direction feature as a class of adjacent directions pointing to the nuclear center to represent the spatial relationship between pixels within the nucleus.
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the exponential growth of multi-hop graph neighborhoods along network layers.
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models.
An Information Theory-inspired Strategy for Automatic Network Pruning
This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
Still, these techniques are faced with a common challenge in practice: Labeled data are limited by the cost of manual extraction from literature and laborious experimentation.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #8 on
Motion Synthesis
on HumanML3D
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
NDF: Neural Deformable Fields for Dynamic Human Modelling
However, the learned canonical representation is static and the current design of the deformation fields is not able to represent large movements or detailed geometry changes.
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Worse, the bad actors found for one graph model severely compromise other models as well.
Carrying out CNN Channel Pruning in a White Box
Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.
Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues
Specifically, our end-to-end model first synthesizes a set of intermediate novel sub-aperture images (SAIs) by exploring the coarse characteristics of the sparsely-sampled LF input with spatial-angular alternating convolutions.
Hyperspectral Image Super-resolution with Deep Priors and Degradation Model Inversion
To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention.
Deep Multiview Clustering by Contrasting Cluster Assignments
Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage.
Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive objectives.
Stochastic Gradient Descent with Biased but Consistent Gradient Estimators
The theory assumes that one can easily compute an unbiased gradient estimator, which is usually the case due to the sample average nature of empirical risk minimization.
Position Embedding Needs an Independent Layer Normalization
By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization
A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs.
Generative Face Video Coding Techniques and Standardization Efforts: A Review
Generative Face Video Coding (GFVC) techniques can exploit the compact representation of facial priors and the strong inference capability of deep generative models, achieving high-quality face video communication in ultra-low bandwidth scenarios.
Hyperspectral and Multispectral Image Fusion Using the Conditional Denoising Diffusion Probabilistic Model
Specifically, the DDPM-Fus contains the forward diffusion process which gradually adds Gaussian noise to the high spatial resolution HSI (HrHSI) and another reverse denoising process which learns to predict the desired HrHSI from its noisy version conditioning on the corresponding high spatial resolution MSI (HrMSI) and low spatial resolution HSI (LrHSI).
Application of Machine Learning in Rock Facies Classification with Physics-Motivated Feature Augmentation
This paper shows the inclusion of physics-motivated feature interaction in feature augmentation can further improve the capability of machine learning in rock facies classification.
Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation
Furthermore, the regularization parameter is simultaneously estimated to automatically adjust contribution of the physical model and {the} learned prior to reconstruct the final HR HSI.
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Moreover, we propose a simple yet effective Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets by learning the neighbor effect for each node.
Linear-Cost Covariance Functions for Gaussian Random Fields
An essential ingredient of GRF is the covariance function that characterizes the joint Gaussian distribution of the field.
Methodology Numerical Analysis
A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion
In order to demonstrate the proposed model's capability in dealing with severe data loss scenarios, we contribute a high-accuracy and challenging motion capture dataset of multi-person interactions with severe occlusion.
Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
The fusion problem is stated as an optimization problem in the maximum a posteriori framework.
Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
Gaussian processes (GPs) are an attractive class of machine learning models because of their simplicity and flexibility as building blocks of more complex Bayesian models.
Sparse Phase Retrieval via Truncated Amplitude Flow
Upon formulating sparse PR as an amplitude-based nonconvex optimization task, SPARTA works iteratively in two stages: In stage one, the support of the underlying sparse signal is recovered using an analytically well-justified rule, and subsequently, a sparse orthogonality-promoting initialization is obtained via power iterations restricted on the support; and, in the second stage, the initialization is successively refined by means of hard thresholding based gradient-type iterations.
Information Theory Information Theory Optimization and Control
Generating a Doppelganger Graph: Resembling but Distinct
Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e. g., images and sound waves).
Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
Deconvolution is a widely used strategy to mitigate the blurring and noisy degradation of hyperspectral images~(HSI) generated by the acquisition devices.
A Plug-and-Play Priors Framework for Hyperspectral Unmixing
Spectral unmixing is a widely used technique in hyperspectral image processing and analysis.
From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
We design a simple yet effective HopGNN framework that can easily utilize existing GNNs to achieve hop interaction.
Learning to Distill Global Representation for Sparse-View CT
The reconstructed images, however, suffer from strong artifacts, greatly limiting their diagnostic value.
Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware Fusion
Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF.
Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms.
Image and Video Processing
AnimeGAN: A Novel Lightweight GAN for Photo Animation
The existing methods usually have some problems, among which significant problems mainly include: 1) the generated images have no obvious animated style textures; 2) the generated images lose the content of the original images; 3) the parameters of the network require the large memory capacity.
Flexible Alignment Super-Resolution Network for Multi-Contrast MRI
To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution.
Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching
To significantly reduce the communication volume without compromising prediction accuracy, we propose a policy for caching data associated with frequently accessed vertices in remote partitions.
Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses
To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input.
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information.
Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks
One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision.
Automated discovery of a robust interatomic potential for aluminum
The accuracy and robustness of an ML potential is primarily limited by the quality and diversity of the training dataset.
Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination
Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process.
GC-Flow: A Graph-Based Flow Network for Effective Clustering
Graph convolutional networks (GCNs) are \emph{discriminative models} that directly model the class posterior $p(y|\mathbf{x})$ for semi-supervised classification of graph data.
Revisiting Random Binning Features: Fast Convergence and Strong Parallelizability
We thus propose the first analysis of RB from the perspective of optimization, which by interpreting RB as a Randomized Block Coordinate Descent in the infinite-dimensional space, gives a faster convergence rate compared to that of other random features.
Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs
Second, we need to learn a consensus graph that captures the high-order interactions between local feature spaces and how to combine them to achieve a better prediction.
Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues
Existing learning-based hyperspectral reconstruction methods show limitations in fully exploiting the information among the hyperspectral bands.
MolSets: Molecular Graph Deep Sets Learning for Mixture Property Modeling
This complexity is particularly evident in molecular mixtures, a frequently explored space for materials such as battery electrolytes.
Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation
In this paper, we propose an end-to-end generic salient object segmentation model called Metric Expression Network (MEnet) to deal with saliency detection with the tolerance of distortion.
Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors
In this paper, we propose a Multi-Preferences Model (MPM) to eliminate the effects of unexpected behaviors.
Multi-view MERA Subspace Clustering
Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor.
A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
The study includes a set of experiments to support the theory and method, including approximating the GW distance, preserving the graph spectrum, classifying graphs using spectral information, and performing regression using graph convolutional networks.
Parallel and distributed asynchronous adaptive stochastic gradient methods
The proposed method is tested on both convex and non-convex machine learning problems, and the numerical results demonstrate its clear advantages over the sync counterpart and the async-parallel nonadaptive SGM.
Optimization and Control Distributed, Parallel, and Cluster Computing Numerical Analysis Numerical Analysis 90C15, 65Y05, 68W15, 65K05
Explainable Neural Networks based on Additive Index Models
In this paper, we present the Explainable Neural Network (xNN), a structured neural network designed especially to learn interpretable features.
Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)
This is in contrast with the KLIME approach that is based on clustering the predictor space.
Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays.
Robust Video Content Alignment and Compensation for Clear Vision Through the Rain
Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes.
Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.
Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications
In this paper, we design and analyze a new zeroth-order online algorithm, namely, the zeroth-order online alternating direction method of multipliers (ZOO-ADMM), which enjoys dual advantages of being gradient-free operation and employing the ADMM to accommodate complex structured regularizers.
Texture Classification in Extreme Scale Variations using GANet
Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding we are developing a new dataset, the Extreme Scale Variation Textures (ESVaT), to test the performance of our framework.
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention.
Hierarchically Compositional Kernels for Scalable Nonparametric Learning
We propose a novel class of kernels to alleviate the high computational cost of large-scale nonparametric learning with kernel methods.
Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions
Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions.
On the Selective and Invariant Representation of DCNN for High-Resolution Remote Sensing Image Recognition
Owing to its superiority in feature representation, DCNN has exhibited remarkable performance in scene recognition of high-resolution remote sensing (HRRS) images and classification of hyper-spectral remote sensing images.
Solving Almost all Systems of Random Quadratic Equations
This paper deals with finding an $n$-dimensional solution $x$ to a system of quadratic equations of the form $y_i=|\langle{a}_i, x\rangle|^2$ for $1\le i \le m$, which is also known as phase retrieval and is NP-hard in general.
What do We Learn by Semantic Scene Understanding for Remote Sensing imagery in CNN framework?
Is the DCNN recognition mechanism centered on object recognition still applicable to the scenarios of remote sensing scene understanding?
Subspace clustering using a symmetric low-rank representation
In this paper, we propose a low-rank representation with symmetric constraint (LRRSC) method for robust subspace clustering.
Light Field Compression with Disparity Guided Sparse Coding based on Structural Key Views
Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world.
Adaptation and learning over networks for nonlinear system modeling
In this chapter, we analyze nonlinear filtering problems in distributed environments, e. g., sensor networks or peer-to-peer protocols.
Multitask diffusion adaptation over networks with common latent representations
Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications.
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.
Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
A novel approach termed \emph{stochastic truncated amplitude flow} (STAF) is developed to reconstruct an unknown $n$-dimensional real-/complex-valued signal $\bm{x}$ from $m$ `phaseless' quadratic equations of the form $\psi_i=|\langle\bm{a}_i,\bm{x}\rangle|$.
On Bochner's and Polya's Characterizations of Positive-Definite Kernels and the Respective Random Feature Maps
A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a probability distribution.
Saliency Integration: An Arbitrator Model
Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model.
HEp-2 Cell Classification: The Role of Gaussian Scale Space Theory as A Pre-processing Approach
We validate the GSS pre-processing under the Local Binary Pattern (LBP) and the Bag-of-Words (BoW) frameworks.
Stochastic Behavior of the Nonnegative Least Mean Fourth Algorithm for Stationary Gaussian Inputs and Slow Learning
Some system identification problems impose nonnegativity constraints on the parameters to estimate due to inherent physical characteristics of the unknown system.
Symmetric low-rank representation for subspace clustering
We propose a symmetric low-rank representation (SLRR) method for subspace clustering, which assumes that a data set is approximately drawn from the union of multiple subspaces.
Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximation
To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complementing a low-rank approximate representation of the full-rank GP based on a support set of inputs with a Markov approximation of the resulting residual process; the latter approximation is guaranteed to be closest in the Kullback-Leibler distance criterion subject to some constraint and is considerably more refined than that of existing sparse GP models utilizing low-rank representations due to its more relaxed conditional independence assumption (especially with larger data).
Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.
Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots.
GP-Localize: Persistent Mobile Robot Localization using Online Sparse Gaussian Process Observation Model
Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements.
Steady-state performance of non-negative least-mean-square algorithm and its variants
The transient behavior of the NNLMS, Normalized NNLMS, Exponential NNLMS and Sign-Sign NNLMS algorithms have been studied in our previous work.
Convergence analysis of kernel LMS algorithm with pre-tuned dictionary
In addition to choosing a reproducing kernel and setting filter parameters, designing a KLMS adaptive filter requires to select a so-called dictionary in order to get a finite-order model.
Nonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization
Incorporating spatial information into hyperspectral unmixing procedures has been shown to have positive effects, due to the inherent spatial-spectral duality in hyperspectral scenes.
Online dictionary learning for kernel LMS. Analysis and forward-backward splitting algorithm
Unfortunately, an undesirable characteristic of these methods is that the order of the filters grows linearly with the number of input data.
Gaussian Process-Based Decentralized Data Fusion and Active Sensing for Mobility-on-Demand System
This paper presents a novel decentralized data fusion and active sensing algorithm for real-time, fine-grained mobility demand sensing and prediction with a fleet of autonomous robotic vehicles in a MoD system.
Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted.
Haze Density Estimation via Modeling of Scattering Coefficients of Iso-depth Regions
Vision based haze density estimation is of practical implications for the purpose of precaution alarm and emergency reactions toward disastrous hazy weathers.
Model Interpretation: A Unified Derivative-based Framework for Nonparametric Regression and Supervised Machine Learning
Interpreting a nonparametric regression model with many predictors is known to be a challenging problem.
Deep Learning for Generic Object Detection: A Survey
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.
Solving Most Systems of Random Quadratic Equations
For certain random measurement models, the proposed procedure returns the true solution $\bm{x}$ with high probability in time proportional to reading the data $\{(\bm{a}_i;y_i)\}_{1\le i \le m}$, provided that the number $m$ of equations is some constant $c>0$ times the number $n$ of unknowns, that is, $m\ge cn$.
Remote Heart Rate Measurement From Face Videos Under Realistic Situations
Heart rate is an important indicator of people's physiological state.
A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation
To the best of our knowledge, this dataset is the first publicly available dataset created in a systematic manner with ground-truth for spectral unmixing.
Stratified Labeling for Surface Consistent Parallax Correction and Occlusion Completion
A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities.
A Sequential Set Generation Method for Predicting Set-Valued Outputs
Though SSG is sequential in nature, it does not penalize the ordering of the appearance of the set elements and can be applied to a variety of set output problems, such as a set of classification labels or sequences.
Time Series Simulation by Conditional Generative Adversarial Net
Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation.
Learning discriminative features in sequence training without requiring framewise labelled data
We propose a novel method which simultaneously models both the sequence discriminative training and the feature discriminative learning within a single network architecture, so that it can learn discriminative deep features in sequence training that obviates the need for presegmented training data.
DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Graph Enhanced Cross-Domain Text-to-SQL Generation
Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations.
Scalable Variational Bayesian Kernel Selection for Sparse Gaussian Process Regression
To achieve this, we represent the probabilistic kernel as an additional variational variable in a variational inference (VI) framework for SGPR models where its posterior belief is learned together with that of the other variational variables (i. e., inducing variables and kernel hyperparameters).
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator
In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.
A multi-label classification method using a hierarchical and transparent representation for paper-reviewer recommendation
Paper-reviewer recommendation task is of significant academic importance for conference chairs and journal editors.
Chart Auto-Encoders for Manifold Structured Data
CAE admits desirable manifold properties that auto-encoders with a flat latent space fail to obey, predominantly proximity of data.
Multitask learning over graphs: An Approach for Distributed, Streaming Machine Learning
Multitask learning is an approach to inductive transfer learning (using what is learned for one problem to assist in another problem) and helps improve generalization performance relative to learning each task separately by using the domain information contained in the training signals of related tasks as an inductive bias.
Embedding Compression with Isotropic Iterative Quantization
Continuous representation of words is a standard component in deep learning-based NLP models.
Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification
The feature-learning procedure of CNN largely depends on the architecture of CNN.
Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection
Instead of blindly trusting quality-inconsistent PAs, WS^2 employs a learning-based selection to select effective PAs and a novel region integrity criterion as a stopping condition for weakly-supervised training.
Adaptive Explainable Neural Networks (AxNNs)
While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results.
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown.
Ranked #8 on
Unsupervised Domain Adaptation
on Duke to Market
Policy Gradient from Demonstration and Curiosity
In this work, an integrated policy gradient algorithm was proposed to boost exploration and facilitate intrinsic reward learning from only limited number of demonstrations.
Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
The linear inverse problem is fundamental to the development of various scientific areas.
Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms
Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive performance over traditional statistical methods.
Supervised Machine Learning Techniques: An Overview with Applications to Banking
This article provides an overview of Supervised Machine Learning (SML) with a focus on applications to banking.
Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution
To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation.
Hyperspectral Unmixing via Nonnegative Matrix Factorization with Handcrafted and Learnt Priors
In our work, we propose an NMF based unmixing framework which jointly uses a handcrafting regularizer and a learnt regularizer from data.
Deep reinforcement learning for RAN optimization and control
Due to the high variability of the traffic in the radio access network (RAN), fixed network configurations are not flexible enough to achieve optimal performance.
Online Convex Optimization Over Erdos-Renyi Random Networks
The regret bounds scaling with respect to $T$ match those obtained by state-of-the-art algorithms and fundamental limits in the corresponding centralized online optimization problems, e. g., $\mathcal{O}(\sqrt{T}) $ and $\mathcal{O}(\ln(T)) $ regrets are established for convex and strongly convex losses with full gradient feedback and two-points information, respectively.
Edge Adaptive Hybrid Regularization Model For Image Deblurring
In the proposed model, it detects the edges and then spatially adjusts the parameters of Tikhonov and TV regularization terms for each pixel according to the edge information.
Handling Noisy Labels via One-Step Abductive Multi-Target Learning and Its Application to Helicobacter Pylori Segmentation
Learning from noisy labels is an important concern in plenty of real-world scenarios.
Hyperspectral Unmixing via Deep Autoencoder Networks for a Generalized Linear-Mixture/Nonlinear-Fluctuation Model
This paper presents an unsupervised nonlinear spectral unmixing method based on a deep autoencoder network that applies to a generalized linear-mixture/nonlinear fluctuation model, consisting of a linear mixture component and an additive nonlinear mixture component that depends on both endmembers and abundances.
Online Graph-Based Change Point Detection in Multiband Image Sequences
To effectively perform change-point detection in multitemporal images, it is important to devise techniques that are computationally efficient for processing large datasets, and that do not require knowledge about the nature of the changes.
On Performance of Multiscale Sparse Fast Fourier Transform Algorithm
The sFFT algorithms decrease the runtime and sampling complexity by taking advantage of the signal inherent characteristics that a large number of signals are sparse in the frequency domain(e. g., sensors, video data, audio, medical image, etc.).
On Performance of Sparse Fast Fourier Transform Algorithms Using the Aliasing Filter
In the second part, we make two categories of experiments for computing the signals of different SNR, different N, different K by a standard testing platform and record the run time, percentage of the signal sampled and L0, L1, L2 error both in the exactly sparse case and general sparse case.
Empirical Evaluation of Typical Sparse Fast Fourier Transform Algorithms
Computing the Sparse Fast Fourier Transform(sFFT) of a K-sparse signal of size N has emerged as a critical topic for a long time.
Transient Theoretical Analysis of Diffusion RLS Algorithm for Cyclostationary Colored Inputs
Convergence of the diffusion RLS (DRLS) algorithm to steady-state has been extensively studied in the literature, whereas no analysis of its transient convergence behavior has been reported yet.
Performance of Domain-Wall Encoding for Quantum Annealing
In this paper we experimentally test the performance of the recently proposed domain-wall encoding of discrete variables from [Chancellor Quantum Sci.
Quantum Physics
Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.
A deep learning-based approach for the automated surface inspection of copper clad laminate images
A machine vision-based surface quality inspection system is usually composed of two processes: image acquisition and automatic defect detection.
Projection-based QLP Algorithm for Efficiently Computing Low-Rank Approximation of Matrices
The efficiency and effectiveness of our proposed PbP-QLP algorithm are investigated through various classes of synthetic and real-world data matrices.
Linear Iterative Feature Embedding: An Ensemble Framework for Interpretable Model
The LIFE algorithm is able to fit a wide single-hidden-layer neural network (NN) accurately with three steps: defining the subsets of a dataset by the linear projections of neural nodes, creating the features from multiple narrow single-hidden-layer NNs trained on the different subsets of the data, combining the features with a linear model.
Resilient Control under Quantization and Denial-of-Service: Co-designing a Deadbeat Controller and Transmission Protocol
When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals.
Noise Injection-based Regularization for Point Cloud Processing
In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.
Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
RR-Net: Injecting Interactive Semantics in Human-Object Interaction Detection
Upon the frame, an Interaction Intensifier Module and a Correlation Parsing Module are carefully designed, where: a) interactive semantics from humans can be exploited and passed to objects to intensify interactions, b) interactive correlations among humans, objects and interactions are integrated to promote predictions.
Geometrical Characterization of Sensor Placement for Cone-Invariant and Multi-Agent Systems against Undetectable Zero-Dynamics Attacks
Undetectable attacks are an important class of malicious attacks threatening the security of cyber-physical systems, which can modify a system's state but leave the system output measurements unaffected, and hence cannot be detected from the output.
Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.
Bias, Fairness, and Accountability with AI and ML Algorithms
In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms.
Composition and Application of Current Advanced Driving Assistance System: A Review
Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price.
Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering
Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence.
Graph coarsening: From scientific computing to machine learning
The general method of graph coarsening or graph reduction has been a remarkably useful and ubiquitous tool in scientific computing and it is now just starting to have a similar impact in machine learning.
Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.
Efficient proximal gradient algorithms for joint graphical lasso
We consider learning an undirected graphical model from sparse data.
Attention-Guided NIR Image Colorization via Adaptive Fusion of Semantic and Texture Clues
Finally, a Fusion Attention Block (FAB) is proposed to adaptively fuse the features from the two branches and generate an optimized colorization result.
On Faster Convergence of Scaled Sign Gradient Descent
For the first two cases, it can be shown that the scaled signGD converges at a linear rate.
Supervised Linear Dimension-Reduction Methods: Review, Extensions, and Comparisons
Principal component analysis (PCA) is a well-known linear dimension-reduction method that has been widely used in data analysis and modeling.
Transient Performance Analysis of the $\ell_1$-RLS
The recursive least-squares algorithm with $\ell_1$-norm regularization ($\ell_1$-RLS) exhibits excellent performance in terms of convergence rate and steady-state error in identification of sparse systems.
Evaluating Robustness of Cooperative MARL
In recent years, a proliferation of methods were developed for multi-agent reinforcement learning (MARL).
