Search Results for author:
Found 84 papers, 19 papers with code
Neural Implementation of Hierarchical Bayesian Inference by Importance Sampling
Here we propose a simple mechanism for Bayesian inference which involves averaging over a few feature detection neurons which fire at a rate determined by their similarity to a sensory stimulus.
Bayesian Probabilistic Co-Subspace Addition
Furthermore, PCSA is extended to tackling and filling missing values, to adapting its sparseness, and to modelling tensor data.
Sparse Additive Text Models with Low Rank Background
This paper extends to propose sparse additive model with low rank background (SAM-LRB), and simple yet efficient estimation.
Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform
This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.
Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
The one-sided $\ell_1$ loss and the linear loss are two popular loss functions for 1bit-CS.
Place classification with a graph regularized deep neural network model
Furthermore, results show that the features automatically learned from the raw input range data can achieve competitive results to the features constructed based on statistical and geometrical information.
Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks
As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples.
Functional Hashing for Compressing Neural Networks
As the complexity of deep neural networks (DNNs) trend to grow to absorb the increasing sizes of data, memory and energy consumption has been receiving more and more attentions for industrial applications, especially on mobile devices.
A Novel Artificial Fish Swarm Algorithm for Pattern Recognition with Convex Optimization
Among these parameters, visual and step are very significant in view of the fact that artificial fish basically move based on these parameters.
Latent Topic Embedding
Topic modeling and word embedding are two important techniques for deriving latent semantics from data.
Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction
Aiming at overexposure correction for computed tomography (CT) reconstruction, we in this paper propose a mixed one-bit compressive sensing (M1bit-CS) to acquire information from both regular and saturated measurements.
Real-time 3D Human Tracking for Mobile Robots with Multisensors
An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D).
Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network
Regularization kernel network is an effective and widely used method for nonlinear regression analysis.
Convergence of Unregularized Online Learning Algorithms
In this paper we study the convergence of online gradient descent algorithms in reproducing kernel Hilbert spaces (RKHSs) without regularization.
Fast and Strong Convergence of Online Learning Algorithms
In this paper, we study the online learning algorithm without explicit regularization terms.
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #5 on
Skeleton Based Action Recognition
on UAV-Human
Generalization Properties of hyper-RKHS and its Applications
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.
Realizing data features by deep nets
Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additional capacity costs.
MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems.
Fine-Grained Named Entity Recognition using ELMo and Wikidata
Fine-grained Named Entity Recognition is a task whereby we detect and classify entity mentions to a large set of types.
Skeleton-Based Action Recognition With Directed Graph Neural Networks
The skeleton data have been widely used for the action recognition tasks since they can robustly accommodate dynamic circumstances and complex backgrounds.
Ranked #7 on
Skeleton Based Action Recognition
on UAV-Human
Gaussian Mixture Marginal Distributions for Modelling Remaining Pipe Wall Thickness of Critical Water Mains in Non-Destructive Evaluation
Rapidly estimating the remaining wall thickness (RWT) is paramount for the non-destructive condition assessment evaluation of large critical metallic pipelines.
Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.
Ranked #55 on
Skeleton Based Action Recognition
on NTU RGB+D
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering
To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously.
Mobility Inference on Long-Tailed Sparse Trajectory
How can we infer such a mobility model from the single trajectory information?
Sub/super-stochastic matrix with applications to bipartite tracking control over signed networks
In the first part, we examine the dynamics of bipartite tracking for first-order MASs, second-order MASs and general linear MASs in the presence of asynchronous interactions, respectively.
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.
Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces
In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.
Ranked #27 on
Skeleton Based Action Recognition
on NTU RGB+D
Leader-Driven Opinion Dynamics in Signed Social Networks With Asynchronous Trust/Distrust Level Evolution
Trust and distrust are common in the opinion interactions among agents in social networks, and they are described by the edges with positive and negative weights in the signed digraph, respectively.
Contrastive Visual-Linguistic Pretraining
We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning.
Social Interactions Clustering MOOC Students: An Exploratory Study
An exploratory study on social interactions of MOOC students in FutureLearn was conducted, to answer "how can we cluster students based on their social interactions?"
Revealing the Hidden Patterns: A Comparative Study on Profiling Subpopulations of MOOC Students
Massive Open Online Courses (MOOCs) exhibit a remarkable heterogeneity of students.
Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week's Activities
While Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback.
Fast algorithms for robust principal component analysis with an upper bound on the rank
The first type of algorithm applies regularization terms on the singular values of a matrix to obtain a low-rank matrix.
Topological charge engineering in lasing bound states in continuum
We experimentally analyze all four observed lasing BICs by imaging their far-field polarization vortices and their associated topological charges.
Optics
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.
Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums
Learners may post their feelings of confusion and struggle in the respective MOOC forums, but with the large volume of posts and high workloads for MOOC instructors, it is unlikely that the instructors can identify all learners requiring intervention.
Multi-modal Scene-compliant User Intention Estimation in Navigation
A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work.
Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks
The second algorithm is a broadcast-like version of CPP (B-CPP), and it also achieves linear convergence rate under the same conditions on the objective functions.
Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs
We consider the decentralized optimization problem, where a network of $n$ agents aims to collaboratively minimize the average of their individual smooth and convex objective functions through peer-to-peer communication in a directed graph.
A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data
Diabetic retinopathy (DR) is one of the major blindness-causing diseases currently known.
Dense Contrastive Visual-Linguistic Pretraining
To overcome these issues, we propose unbiased Dense Contrastive Visual-Linguistic Pretraining (DCVLP), which replaces the region regression and classification with cross-modality region contrastive learning that requires no annotations.
Learning with Asymmetric Kernels: Least Squares and Feature Interpretation
Asymmetric kernels naturally exist in real life, e. g., for conditional probability and directed graphs.
Solving parametric partial differential equations with deep rectified quadratic unit neural networks
In this study, we investigate the expressive power of deep rectified quadratic unit (ReQU) neural networks for approximating the solution maps of parametric PDEs.
G2GT: Retrosynthesis Prediction with Graph to Graph Attention Neural Network and Self-Training
Retrosynthesis prediction is one of the fundamental challenges in organic chemistry and related fields.
Coefficient-based Regularized Distribution Regression
Compared with the kernel methods for distribution regression in the literature, the algorithm under consideration does not require the kernel to be symmetric and positive semi-definite and hence provides a simple paradigm for designing indefinite kernel methods, which enriches the theme of the distribution regression.
INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency.
Decision Making
Explainable Artificial Intelligence (XAI)
+2
Capacity dependent analysis for functional online learning algorithms
This article provides convergence analysis of online stochastic gradient descent algorithms for functional linear models.
Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate
In the proposed family, EquiStatic has a degree of $\Theta(\ln(n))$, where $n$ is the network size, and a series of time-dependent one-peer topologies, EquiDyn, has a constant degree of 1.
Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression
Previous analysis of regularized functional linear regression in a reproducing kernel Hilbert space (RKHS) typically requires the target function to be contained in this kernel space.
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
Exit options sustain altruistic punishment and decrease the second-order free-riders, but it is not a panacea
Altruistic punishment, where individuals incur personal costs to punish others who have harmed third parties, presents an evolutionary conundrum as it undermines individual fitness.
Cross-modal information fusion for voice spoofing detection
Researchers have proposed many methods to defend against these attacks, but in the existing methods, researchers just focus on speech features.
Ranked #1 on
Voice Anti-spoofing
on ASVspoof 2019 - PA
Pairwise Ranking with Gaussian Kernels
Regularized pairwise ranking with Gaussian kernels is one of the cutting-edge learning algorithms.
Optimality of Robust Online Learning
In this paper, we study an online learning algorithm with a robust loss function $\mathcal{L}_{\sigma}$ for regression over a reproducing kernel Hilbert space (RKHS).
Impact-Oriented Contextual Scholar Profiling using Self-Citation Graphs
Experiment outcomes show that the F1 score of best GF profile significantly outperforms alternative methods of impact indicators and bibliometric networks in all the 6 computer science fields considered.
STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation
Deep learning based models for medical image segmentation have made great progress in recent years.
Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications.
OSP: Boosting Distributed Model Training with 2-stage Synchronization
However, these two types of methods can result in accuracy loss due to discarded gradients and have limited enhancement on the throughput of model synchronization, respectively.
Classification with Deep Neural Networks and Logistic Loss
In this paper, we aim to fill this gap by establishing a novel and elegant oracle-type inequality, which enables us to deal with the boundedness restriction of the target function, and using it to derive sharp convergence rates for fully connected ReLU DNN classifiers trained with logistic loss.
Solving PDEs on Spheres with Physics-Informed Convolutional Neural Networks
In this paper, we establish rigorous analysis of the physics-informed convolutional neural network (PICNN) for solving PDEs on the sphere.
Enhancing Kernel Flexibility via Learning Asymmetric Locally-Adaptive Kernels
To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel.
GraphGPT: Graph Instruction Tuning for Large Language Models
In this work, we present the GraphGPT framework that aligns LLMs with graph structural knowledge with a graph instruction tuning paradigm.
$\mathbb{VD}$-$\mathbb{GR}$: Boosting $\mathbb{V}$isual $\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\mathbb{GR}$aphs
We propose $\mathbb{VD}$-$\mathbb{GR}$ - a novel visual dialog model that combines pre-trained language models (LMs) with graph neural networks (GNNs).
A Comparative Analysis of the COVID-19 Infodemic in English and Chinese: Insights from Social Media Textual Data
This paper presents a comparative analysis of the COVID-19 infodemic in the English and Chinese languages, utilizing textual data extracted from social media platforms.
Improving Self-supervised Molecular Representation Learning using Persistent Homology
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets.
Neural Reasoning About Agents' Goals, Preferences, and Actions
We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations.
RJUA-QA: A Comprehensive QA Dataset for Urology
We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications.
Mindful Explanations: Prevalence and Impact of Mind Attribution in XAI Research
When users perceive AI systems as mindful, independent agents, they hold them responsible instead of the AI experts who created and designed these systems.
Zero-Inflated Bandits
Many real applications of bandits have sparse non-zero rewards, leading to slow learning rates.
Learning Operators with Stochastic Gradient Descent in General Hilbert Spaces
This study investigates leveraging stochastic gradient descent (SGD) to learn operators between general Hilbert spaces.
HiGPT: Heterogeneous Graph Language Model
However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets.
UrbanGPT: Spatio-Temporal Large Language Models
These findings highlight the potential of building large language models for spatio-temporal learning, particularly in zero-shot scenarios where labeled data is scarce.
Self-Supervised Representation Learning with Meta Comprehensive Regularization
Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features.
A Safe Screening Rule with Bi-level Optimization of $ν$ Support Vector Machine
Support vector machine (SVM) has achieved many successes in machine learning, especially for a small sample problem.
Spectral Algorithms on Manifolds through Diffusion
Our paper introduces a new perspective, asserting that input data are situated within a low-dimensional manifold embedded in a higher-dimensional Euclidean space.
ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos
We show that by adding action embeddings into the noise mask the diffusion model can better learn action temporal dependencies and increase the performances on procedure planning.
An Optimization Framework to Personalize Passive Cardiac Mechanics
The iFEA framework relies on a novel nested optimization scheme, in which the outer iterations utilize a traditional optimization method to best approximate material parameters that fit image data, while the inner iterations employ an augmented Sellier's algorithm to estimate the stress-free reference configuration.
Solving Parametric PDEs with Radial Basis Functions and Deep Neural Networks
We propose the POD-DNN, a novel algorithm leveraging deep neural networks (DNNs) along with radial basis functions (RBFs) in the context of the proper orthogonal decomposition (POD) reduced basis method (RBM), aimed at approximating the parametric mapping of parametric partial differential equations on irregular domains.
Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition
Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.
