Search Results for author: Jie Shen

Found 45 papers, 9 papers with code

An Element-wise RSAV Algorithm for Unconstrained Optimization Problems

no code implementations7 Sep 2023 Shiheng Zhang, Jiahao Zhang, Jie Shen, Guang Lin

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

no code implementations9 Jun 2023 Jiahao Zhang, Shiheng Zhang, Jie Shen, Guang Lin

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.

Operator learning

Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise

no code implementations1 Jun 2023 Shiwei Zeng, Jie Shen

The concept class of low-degree polynomial threshold functions (PTFs) plays a fundamental role in machine learning.

PAC learning

Learning Large Scale Sparse Models

no code implementations26 Jan 2023 Atul Dhingra, Jie Shen, Nicholas Kleene

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

no code implementations11 Nov 2022 Jing Yang, Jie Shen, Yiming Lin, Yordan Hristov, Maja Pantic

Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences.

Action Unit Detection Face Alignment +2

Training Strategies for Improved Lip-reading

1 code implementation3 Sep 2022 Pingchuan Ma, Yujiang Wang, Stavros Petridis, Jie Shen, Maja Pantic

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 #1 on Lipreading on Lip Reading in the Wild (using extra training data)

Data Augmentation Lipreading +1

List-Decodable Sparse Mean Estimation

no code implementations28 May 2022 Shiwei Zeng, Jie Shen

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

no code implementations24 Mar 2022 Yujiang Wang, Mingzhi Dong, Jie Shen, Yiming Luo, Yiming Lin, Pingchuan Ma, Stavros Petridis, Maja Pantic

We also investigate face clustering in egocentric videos, a fast-emerging field that has not been studied yet in works related to face clustering.

Clustering Contrastive Learning +1

FAHP-based Mathematical Model for Exercise Rehabilitation Management of Diabetes Mellitus

no code implementations7 Jan 2022 Daoyan Pan, Kewei Wang, Zhiheng Zhou, Xingran Liu, Jie Shen

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

no code implementations18 Oct 2021 Rafael Poyiadzi, Jie Shen, Stavros Petridis, Yujiang Wang, Maja Pantic

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

1 code implementation9 Jul 2021 Jacob Donley, Vladimir Tourbabin, Jung-Suk Lee, Mark Broyles, Hao Jiang, Jie Shen, Maja Pantic, Vamsi Krishna Ithapu, Ravish Mehra

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.

Speech Enhancement

FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild

1 code implementation21 Jun 2021 Yiming Lin, Jie Shen, Yujiang Wang, Maja Pantic

To evaluate our method on in-the-wild data, we also introduce a new challenging large-scale benchmark called IMDB-Clean.

Age Estimation Constrained Clustering +1

Semi-verified PAC Learning from the Crowd

no code implementations13 Jun 2021 Shiwei Zeng, Jie Shen

We study the problem of crowdsourced PAC learning of threshold functions.

PAC learning TAG

Identity Inference on Blockchain using Graph Neural Network

1 code implementation14 Apr 2021 Jie Shen, Jiajun Zhou, Yunyi Xie, Shanqing Yu, Qi Xuan

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.

Graph Classification Graph Mining

Sample-Optimal PAC Learning of Halfspaces with Malicious Noise

no code implementations11 Feb 2021 Jie Shen

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.

PAC learning

RoI Tanh-polar Transformer Network for Face Parsing in the Wild

2 code implementations4 Feb 2021 Yiming Lin, Jie Shen, Yujiang Wang, Maja Pantic

Face parsing aims to predict pixel-wise labels for facial components of a target face in an image.

Face Parsing

Uncertainty-Based Adaptive Learning for Reading Comprehension

no code implementations1 Jan 2021 Jing Wang, Jie Shen, Xiaofei Ma, Andrew Arnold

Recent years have witnessed a surge of successful applications of machine reading comprehension.

Machine Reading Comprehension

On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise

no code implementations19 Dec 2020 Jie Shen

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 $\tilde{O}\big(\frac{d}{\epsilon} \big)$.

Active Learning

Efficient PAC Learning from the Crowd with Pairwise Comparisons

no code implementations2 Nov 2020 Shiwei Zeng, Jie Shen

We study crowdsourced PAC learning of threshold functions, where the labels are gathered from a pool of annotators some of whom may behave adversarially.

PAC learning

Lip-reading with Densely Connected Temporal Convolutional Networks

1 code implementation29 Sep 2020 Pingchuan Ma, Yujiang Wang, Jie Shen, Stavros Petridis, Maja Pantic

In this work, we present the Densely Connected Temporal Convolutional Network (DC-TCN) for lip-reading of isolated words.

Lip Reading

M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification

no code implementations11 Jul 2020 Jiajun Zhou, Jie Shen, Shanqing Yu, Guanrong Chen, Qi Xuan

Graph classification, which aims to identify the category labels of graphs, plays a significant role in drug classification, toxicity detection, protein analysis etc.

Data Augmentation General Classification +1

One-Bit Compressed Sensing via One-Shot Hard Thresholding

no code implementations7 Jul 2020 Jie Shen

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

no code implementations6 Jun 2020 Jie Shen, Chicheng Zhang

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.

Active Learning Open-Ended Question Answering

Efficient active learning of sparse halfspaces with arbitrary bounded noise

no code implementations NeurIPS 2020 Chicheng Zhang, Jie Shen, Pranjal Awasthi

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.

Active Learning

Towards Pose-invariant Lip-Reading

no code implementations14 Nov 2019 Shiyang Cheng, Pingchuan Ma, Georgios Tzimiropoulos, Stavros Petridis, Adrian Bulat, Jie Shen, Maja Pantic

The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views.

Lip Reading

Shape Constrained Network for Eye Segmentation in the Wild

no code implementations11 Oct 2019 Bingnan Luo, Jie Shen, Shiyang Cheng, Yujiang Wang, Maja Pantic

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.

Segmentation Semantic Segmentation

Dynamic Face Video Segmentation via Reinforcement Learning

no code implementations CVPR 2020 Yujiang Wang, Mingzhi Dong, Jie Shen, Yang Wu, Shiyang Cheng, Maja Pantic

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.

reinforcement-learning Reinforcement Learning (RL) +4

SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild

no code implementations9 Jan 2019 Jean Kossaifi, Robert Walecki, Yannis Panagakis, Jie Shen, Maximilian Schmitt, Fabien Ringeval, Jing Han, Vedhas Pandit, Antoine Toisoul, Bjorn Schuller, Kam Star, Elnar Hajiyev, Maja Pantic

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

no code implementations24 Jul 2018 Yujiang Wang, Bingnan Luo, Jie Shen, Maja Pantic

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.

Image Segmentation Segmentation +1

MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild

1 code implementation24 May 2018 Yiming Lin, Shiyang Cheng, Jie Shen, Maja Pantic

36 state-of-the-art trackers, including facial landmark trackers, generic object trackers and trackers that we have fine-tuned or improved, are evaluated.

Face Detection Object Tracking +1

A real-time and unsupervised face Re-Identification system for Human-Robot Interaction

1 code implementation10 Apr 2018 Yujiang Wang, Jie Shen, Stavros Petridis, Maja Pantic

In this paper, we present an effective and unsupervised face Re-ID system which simultaneously re-identifies multiple faces for HRI.

Clustering Face Recognition +1

Visual-Only Recognition of Normal, Whispered and Silent Speech

no code implementations18 Feb 2018 Stavros Petridis, Jie Shen, Doruk Cetin, Maja Pantic

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.

speech-recognition Visual Speech Recognition

Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery

no code implementations NeurIPS 2017 Jie Shen, Ping Li

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

no code implementations ICML 2017 Jie Shen, Ping Li

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

no code implementations COLING 2016 Jie Shen, Cong Liu

Distributed word representation is an efficient method for capturing semantic and syntactic word relations.

Dependency Parsing Language Modelling +5

A Tight Bound of Hard Thresholding

no code implementations5 May 2016 Jie Shen, Ping Li

This paper is concerned with the hard thresholding operator which sets all but the $k$ largest absolute elements of a vector to zero.

BIG-bench Machine Learning

Social Trust Prediction via Max-norm Constrained 1-bit Matrix Completion

no code implementations24 Apr 2015 Jing Wang, Jie Shen, Huan Xu

Social trust prediction addresses the significant problem of exploring interactions among users in social networks.

Matrix Completion

Efficient Online Minimization for Low-Rank Subspace Clustering

no code implementations28 Mar 2015 Jie Shen, Ping Li, Huan Xu

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

no code implementations5 Feb 2015 Jing Wang, Jie Shen, Ping Li

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

no code implementations NeurIPS 2014 Jie Shen, Huan Xu, Ping Li

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.

Matrix Completion

A Latent Clothing Attribute Approach for Human Pose Estimation

no code implementations16 Nov 2014 Weipeng Zhang, Jie Shen, Guangcan Liu, Yong Yu

Unlike previous approaches, our approach models the clothing attributes as latent variables and thus requires no explicit labeling for the clothing attributes.

Action Recognition Pose Estimation +2

Online Optimization for Large-Scale Max-Norm Regularization

no code implementations12 Jun 2014 Jie Shen, Huan Xu, Ping Li

Max-norm regularizer has been extensively studied in the last decade as it promotes an effective low-rank estimation for the underlying data.

Matrix Completion

Unified Structured Learning for Simultaneous Human Pose Estimation and Garment Attribute Classification

no code implementations19 Apr 2014 Jie Shen, Guangcan Liu, Jia Chen, Yuqiang Fang, Jianbin Xie, Yong Yu, Shuicheng Yan

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.

General Classification Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.