Search Results for author:
Found 47 papers, 10 papers with code
Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
Understanding noise tolerance of machine learning algorithms is a central quest in learning theory.
FedLED: Label-Free Equipment Fault Diagnosis with Vertical Federated Transfer Learning
Intelligent equipment fault diagnosis based on Federated Transfer Learning (FTL) attracts considerable attention from both academia and industry.
An Element-wise RSAV Algorithm for Unconstrained Optimization Problems
We present a novel optimization algorithm, element-wise relaxed scalar auxiliary variable (E-RSAV), that satisfies an unconditional energy dissipation law and exhibits improved alignment between the modified and the original energy.
Energy-Dissipative Evolutionary Deep Operator Neural Networks
For an objective operator G, the Branch net encodes different input functions u at the same number of sensors, and the Trunk net evaluates the output function at any location.
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
The concept class of low-degree polynomial threshold functions (PTFs) plays a fundamental role in machine learning.
Learning Large Scale Sparse Models
In particular, the memory issue precludes a large volume of prior algorithms that are based on batch optimization technique.
FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection
Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences.
Training Strategies for Improved Lip-reading
In this paper, we systematically investigate the performance of state-of-the-art data augmentation approaches, temporal models and other training strategies, like self-distillation and using word boundary indicators.
Ranked #2 on
Lipreading
on Lip Reading in the Wild
(using extra training data)
List-Decodable Sparse Mean Estimation
Robust mean estimation is one of the most important problems in statistics: given a set of samples in $\mathbb{R}^d$ where an $\alpha$ fraction are drawn from some distribution $D$ and the rest are adversarially corrupted, we aim to estimate the mean of $D$.
Self-supervised Video-centralised Transformer for Video Face Clustering
We also investigate face clustering in egocentric videos, a fast-emerging field that has not been studied yet in works related to face clustering.
Ranked #1 on
Face Clustering
on EasyCom
FAHP-based Mathematical Model for Exercise Rehabilitation Management of Diabetes Mellitus
Exercise rehabilitation is an important part in the comprehensive management of patients with diabetes and there is a need to conduct comprehensively evaluation of several factors such as the physical fitness, cardiovascular risk and diabetic disease factors.
Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups
We then study the effect of variety and number of age-groups used during training on generalisation to unseen age-groups and observe that an increase in the number of training age-groups tends to increase the apparent emotional facial expression recognition performance on unseen age-groups.
Facial Expression Recognition
Facial Expression Recognition (FER)
EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments
In this work, we describe, evaluate and release a dataset that contains over 5 hours of multi-modal data useful for training and testing algorithms for the application of improving conversations for an AR glasses wearer.
Ranked #1 on
Speech Enhancement
on EasyCom
FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild
To evaluate our method on in-the-wild data, we also introduce a new challenging large-scale benchmark called IMDB-Clean.
Ranked #1 on
Age Estimation
on KANFace
Semi-verified PAC Learning from the Crowd
We study the problem of crowdsourced PAC learning of threshold functions.
Identity Inference on Blockchain using Graph Neural Network
In this paper, we present a novel approach to analyze user's behavior from the perspective of the transaction subgraph, which naturally transforms the identity inference task into a graph classification pattern and effectively avoids computation in large-scale graph.
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
We further extend the algorithm and analysis to the more general and stronger nasty noise model of Bshouty et al. (2002), showing that it is still possible to achieve near-optimal noise tolerance and sample complexity in polynomial time.
RoI Tanh-polar Transformer Network for Face Parsing in the Wild
Face parsing aims to predict pixel-wise labels for facial components of a target face in an image.
Ranked #1 on
Face Parsing
on iBugMask
Uncertainty-Based Adaptive Learning for Reading Comprehension
Recent years have witnessed a surge of successful applications of machine reading comprehension.
On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise
Our main contribution is a Perceptron-like online active learning algorithm that runs in polynomial time, and under the conditions that the marginal distribution is isotropic log-concave and $\nu = \Omega(\epsilon)$, where $\epsilon \in (0, 1)$ is the target error rate, our algorithm PAC learns the underlying halfspace with near-optimal label complexity of $\tilde{O}\big(d \cdot polylog(\frac{1}{\epsilon})\big)$ and sample complexity of $\tilde{O}\big(\frac{d}{\epsilon} \big)$.
Efficient PAC Learning from the Crowd with Pairwise Comparisons
We study crowdsourced PAC learning of threshold functions, where the labels are gathered from a pool of annotators some of whom may behave adversarially.
Lip-reading with Densely Connected Temporal Convolutional Networks
In this work, we present the Densely Connected Temporal Convolutional Network (DC-TCN) for lip-reading of isolated words.
M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
Graph classification, which aims to identify the category labels of graphs, plays a significant role in drug classification, toxicity detection, protein analysis etc.
One-Bit Compressed Sensing via One-Shot Hard Thresholding
This paper concerns the problem of 1-bit compressed sensing, where the goal is to estimate a sparse signal from a few of its binary measurements.
Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance
We answer this question in the affirmative by designing a computationally efficient active learning algorithm with near-optimal label complexity of $\tilde{O}\big({s \log^4 \frac d \epsilon} \big)$ and noise tolerance $\eta = \Omega(\epsilon)$, where $\epsilon \in (0, 1)$ is the target error rate, under the assumption that the distribution over (uncorrupted) unlabeled examples is isotropic log-concave.
Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
Introducing LI mechanisms improves the convolutional filter's sensitivity to semantic object boundaries.
Efficient active learning of sparse halfspaces with arbitrary bounded noise
Even in the presence of mild label noise, i. e. $\eta$ is a small constant, this is a challenging problem and only recently have label complexity bounds of the form $\tilde{O}\big(s \cdot \mathrm{polylog}(d, \frac{1}{\epsilon})\big)$ been established in [Zhang, 2018] for computationally efficient algorithms.
Towards Pose-invariant Lip-Reading
The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views.
Shape Constrained Network for Eye Segmentation in the Wild
Specifically, we learn the shape prior from our dataset using VAE-GAN, and leverage the pre-trained encoder and discriminator to regularise the training of SegNet.
Dynamic Face Video Segmentation via Reinforcement Learning
To the best of our knowledge, this is the first work to use reinforcement learning for online key-frame decision in dynamic video segmentation, and also the first work on its application on face videos.
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild
Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are increasingly becoming an indispensable part of our life.
Face Mask Extraction in Video Sequence
Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence.
Provable Variable Selection for Streaming Features
As a remedy, online feature selection has attracted increasing attention in recent years.
MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild
36 state-of-the-art trackers, including facial landmark trackers, generic object trackers and trackers that we have fine-tuned or improved, are evaluated.
A real-time and unsupervised face Re-Identification system for Human-Robot Interaction
In this paper, we present an effective and unsupervised face Re-ID system which simultaneously re-identifies multiple faces for HRI.
Visual-Only Recognition of Normal, Whispered and Silent Speech
We show that an absolute decrease in classification rate of up to 3. 7% is observed when training and testing on normal and whispered, respectively, and vice versa.
Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery
In machine learning and compressed sensing, it is of central importance to understand when a tractable algorithm recovers the support of a sparse signal from its compressed measurements.
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
Recovering the support of a sparse signal from its compressed samples has been one of the most important problems in high dimensional statistics.
Improved Word Embeddings with Implicit Structure Information
Distributed word representation is an efficient method for capturing semantic and syntactic word relations.
A Tight Bound of Hard Thresholding
This paper is concerned with the hard thresholding operator which sets all but the $k$ largest absolute elements of a vector to zero.
Social Trust Prediction via Max-norm Constrained 1-bit Matrix Completion
Social trust prediction addresses the significant problem of exploring interactions among users in social networks.
Efficient Online Minimization for Low-Rank Subspace Clustering
Low-rank representation~(LRR) has been a significant method for segmenting data that are generated from a union of subspaces.
Object Proposal with Kernelized Partial Ranking
In order to determine a small set of proposals with a high recall, a common scheme is extracting multiple features followed by a ranking algorithm which however, incurs two major challenges: {\bf 1)} The ranking model often imposes pairwise constraints between each proposal, rendering the problem away from an efficient training/testing phase; {\bf 2)} Linear kernels are utilized due to the computational and memory bottleneck of training a kernelized model.
Online Optimization for Max-Norm Regularization
The key technique in our algorithm is to reformulate the max-norm into a matrix factorization form, consisting of a basis component and a coefficients one.
A Latent Clothing Attribute Approach for Human Pose Estimation
Unlike previous approaches, our approach models the clothing attributes as latent variables and thus requires no explicit labeling for the clothing attributes.
Online Optimization for Large-Scale Max-Norm Regularization
Max-norm regularizer has been extensively studied in the last decade as it promotes an effective low-rank estimation for the underlying data.
Unified Structured Learning for Simultaneous Human Pose Estimation and Garment Attribute Classification
In this paper, we utilize structured learning to simultaneously address two intertwined problems: human pose estimation (HPE) and garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia applications.
