Search Results for author: Fan Zhang

Found 143 papers, 30 papers with code

Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits

no code implementations ICML 2020 Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet

We first present a policy evaluation procedure in the ambiguous environment and also give a heuristic algorithm to solve the distributionally robust policy learning problems efficiently.

Multi-Armed Bandits

软件标识符的自然语言规范性研究(Research on the Natural Language Normalness of Software Identifiers)

no code implementations CCL 2021 Dongzhen Wen, Fan Zhang, Xiao Zhang, Liang Yang, Yuan Lin, Bo Xu, Hongfei Lin

“软件源代码的理解则是软件协同开发与维护的核心, 而源代码中占半数以上的标识符的理解则在软件理解中起到重要作用, 传统软件工程主要研究通过命名规范限制标识符的命名过程以构造更易理解和交流的标识符。本文则在梳理分析常见编程语言命名规范的基础上, 提出一种全新的标识符可理解性评价标准。具体而言, 本文首先总结梳理了常见主流编程语言中的命名规范并类比自然语言语素概念本文提出基于软件语素的标识符构成过程, 即标识符的构成可被视为软件语素的生成、排列和连接过程。在此基础上, 本文提出一种结合自然语料库的软件标识符规范性评价方法, 用来衡量软件标识符是否易于理解。最后, 本文通过源代码理解数据集和乇乩乴乨乵乢平台中开源项目对规范性指标进行了验证性实验, 结果表明本文提出的规范性分数能够很好衡量软件项目的可理解性。”

Enhancing VVC with Deep Learning based Multi-Frame Post-Processing

no code implementations19 May 2022 Duolikun Danier, Chen Feng, Fan Zhang, David Bull

This paper describes a CNN-based multi-frame post-processing approach based on a perceptually-inspired Generative Adversarial Network architecture, CVEGAN.

Frame Image Compression

A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding

no code implementations14 May 2022 Chuanbo Hu, Shan Jia, Fan Zhang, Xin Li

However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e. g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters.

Image Inpainting Object Detection +1

One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code

no code implementations12 May 2022 Yong Dai, Duyu Tang, Liangxin Liu, Minghuan Tan, Cong Zhou, Jingquan Wang, Zhangyin Feng, Fan Zhang, Xueyu Hu, Shuming Shi

Moreover, our model supports self-supervised pretraining with the same sparsely activated way, resulting in better initialized parameters for different modalities.

Image Retrieval Text-to-Image Retrieval

Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services

no code implementations5 May 2022 Fan Zhang, Qiuying Peng, Yulin Wu, Zheng Pan, Rong Zeng, Da Lin, Yue Qi

Recently, industrial recommendation services have been boosted by the continual upgrade of deep learning methods.

Graph Learning

DFC: Anatomically Informed Fiber Clustering with Self-supervised Deep Learning for Fast and Effective Tractography Parcellation

1 code implementation2 May 2022 Yuqian Chen, Chaoyi Zhang, Tengfei Xue, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell

In this work, we propose a novel deep learning framework for WMFC, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances.

Representation Learning Self-Supervised Learning

SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach

no code implementations26 Apr 2022 Junwei Liao, Duyu Tang, Fan Zhang, Shuming Shi

We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model.

Multi-Task Learning Text Generation

Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer

no code implementations18 Apr 2022 Yangrun Hu, Yuanfan Guo, Fan Zhang, Mingda Wang, Tiancheng Lin, Rong Wu, Yi Xu

Based on the insight that mass data is sufficient and shares the same knowledge structure with non-mass data of identifying the malignancy of a lesion based on the ultrasound image, we propose a novel transfer learning framework to enhance the generalizability of the DNN model for non-mass BUS with the help of mass BUS.

Transfer Learning

Global Attitude Synchronization of Networked Rigid Bodies Under Directed Topologies

no code implementations30 Mar 2022 Fan Zhang, Deyuan Meng, Jingyao Zhang

Simulations for networked spacecraft are presented to show the global synchronization performances under different directed topologies.

STICC: A multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity

1 code implementation17 Mar 2022 Yuhao Kang, Kunlin Wu, Song Gao, Ignavier Ng, Jinmeng Rao, Shan Ye, Fan Zhang, Teng Fei

In this paper, we propose a Spatial Toeplitz Inverse Covariance-Based Clustering (STICC) method that considers both attributes and spatial relationships of geographic objects for multivariate spatial clustering.

Mixed Reality Depth Contour Occlusion Using Binocular Similarity Matching and Three-dimensional Contour Optimisation

no code implementations4 Mar 2022 Naye Ji, Fan Zhang, Haoxiang Zhang, Youbing Zhao, Dingguo Yu

To evaluate the effectiveness of the algorithm, we demonstrate a time con-sumption statistical analysis for each stage of the DCO algorithm execution.

Mixed Reality Optical Flow Estimation +1

A CNN-based Post-Processor for Perceptually-Optimized Immersive Media Compression

no code implementations25 Feb 2022 Angeliki Katsenou, Fan Zhang, David Bull

In recent years, resolution adaptation based on deep neural networks has enabled significant performance gains for conventional (2D) video codecs.

Double Thompson Sampling in Finite stochastic Games

no code implementations21 Feb 2022 Shuqing Shi, Xiaobin Wang, Zhiyou Yang, Fan Zhang, Hong Qu

This algorithm achieves a total regret bound of $\tilde{\mathcal{O}}(D\sqrt{SAT})$in time horizon $T$ with $S$ states, $A$ actions and diameter $D$.

Deep VQA based on a Novel Hybrid Training Methodology

no code implementations17 Feb 2022 Chen Feng, Fan Zhang, David R. Bull

In recent years, deep learning techniques have been widely applied to video quality assessment (VQA), showing significant potential to achieve higher correlation performance with subjective opinions compared to conventional approaches.

Video Quality Assessment Visual Question Answering +1

A Subjective Quality Study for Video Frame Interpolation

no code implementations15 Feb 2022 Duolikun Danier, Fan Zhang, David Bull

Video frame interpolation (VFI) is one of the fundamental research areas in video processing and there has been extensive research on novel and enhanced interpolation algorithms.

Frame SSIM +1

Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN

no code implementations15 Feb 2022 Duolikun Danier, Fan Zhang, David Bull

This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction.

Frame Video Frame Interpolation

SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning

1 code implementation29 Jan 2022 Tengfei Xue, Fan Zhang, Chaoyi Zhang, Yuqian Chen, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Lauren J. O'Donnell

Most parcellation methods focus on the deep white matter (DWM), while fewer methods address the superficial white matter (SWM) due to its complexity.

Contrastive Learning

Empirical Analysis of EIP-1559: Transaction Fees, Waiting Time, and Consensus Security

1 code implementation14 Jan 2022 Yulin Liu, Yuxuan Lu, Kartik Nayak, Fan Zhang, Luyao Zhang, Yinhong Zhao

We conduct a rigorous and comprehensive empirical study to examine its causal effect on blockchain transaction fee dynamics, transaction waiting time and security.

ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation

1 code implementation30 Nov 2021 Duolikun Danier, Fan Zhang, David Bull

Video frame interpolation (VFI) is currently a very active research topic, with applications spanning computer vision, post production and video encoding.

Frame Texture Synthesis +1

Can Graph Neural Networks Learn to Solve MaxSAT Problem?

no code implementations15 Nov 2021 Minghao Liu, Fuqi Jia, Pei Huang, Fan Zhang, Yuchen Sun, Shaowei Cai, Feifei Ma, Jian Zhang

With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning.

Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends

no code implementations5 Nov 2021 Lingying Huang, Xiaomeng Chen, Wei Huo, Jiazheng Wang, Fan Zhang, Bo Bai, Ling Shi

In order to improve the speed of B&B algorithms, learning techniques have been introduced in this algorithm recently.

Variable Selection

Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision

no code implementations6 Oct 2021 Ruijie Ren, Mohit Gurnani Rajesh, Jordi Sanchez-Riera, Fan Zhang, Yurun Tian, Antonio Agudo, Yiannis Demiris, Krystian Mikolajczyk, Francesc Moreno-Noguer

We show that training our network solely with synthetic data and the proposed DA yields results competitive with models trained on real data.

Domain Adaptation

Coded Computation across Shared Heterogeneous Workers with Communication Delay

no code implementations23 Sep 2021 Yuxuan Sun, Fan Zhang, Junlin Zhao, Sheng Zhou, Zhisheng Niu, Deniz Gündüz

In this work, we consider a multi-master heterogeneous-worker distributed computing scenario, where multiple matrix multiplication tasks are encoded and allocated to workers for parallel computation.

Distributed Computing

Efficient Context-Aware Network for Abdominal Multi-organ Segmentation

1 code implementation22 Sep 2021 Fan Zhang, Yu Wang, Hua Yang

For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.

DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis

no code implementations13 Sep 2021 Tiange Xiang, Yang song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, Weidong Cai

With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.

Classification whole slide images

Session-based Recommendation with Heterogeneous Graph Neural Network

no code implementations12 Aug 2021 Jinpeng Chen, Haiyang Li, Fan Zhang, Senzhang Wang, Kaimin Wei

The current studies generally learn user preferences according to the transitions of items in the user's session sequence.

Session-Based Recommendations

Ultralow complexity long short-term memory network for fiber nonlinearity mitigation in coherent optical communication systems

no code implementations12 Aug 2021 Hao Ming, Xinyu Chen, Xiansong Fang, Lei Zhang, Chenjia Li, Fan Zhang

In this paper, we propose a center-oriented long short-term memory network (Co-LSTM) incorporating a simplified mode with a recycling mechanism in the equalization operation, which can mitigate fiber nonlinearity in coherent optical communication systems with ultralow complexity.

On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation

no code implementations ACL 2021 Wei zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.

An explainable two-dimensional single model deep learning approach for Alzheimer's disease diagnosis and brain atrophy localization

no code implementations28 Jul 2021 Fan Zhang, Bo Pan, Pengfei Shao, Peng Liu, Shuwei Shen, Peng Yao, Ronald X. Xu

In this research, we propose a novel end-to-end deep learning approach for automated diagnosis of AD and localization of important brain regions related to the disease from sMRI data.

Data Augmentation

Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation

no code implementations11 Jul 2021 Yuqian Chen, Chaoyi Zhang, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell

White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.

Self-Supervised Learning

Learning Temporal Consistency for Low Light Video Enhancement From Single Images

1 code implementation CVPR 2021 Fan Zhang, Yu Li, ShaoDi You, Ying Fu

Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.

Optical Flow Estimation Video Enhancement

An adaptive Lagrange multiplier determination method for rate-distortion optimisation in hybrid video codecs

no code implementations15 Jun 2021 Fan Zhang, David R. Bull

This paper describes an adaptive Lagrange multiplier determination method for rate-quality optimisation in video compression.

Video Compression

Quality assessment methods for perceptual video compression

no code implementations15 Jun 2021 Fan Zhang, David R. Bull

This paper describes a quality assessment model for perceptual video compression applications (PVM), which stimulates visual masking and distortion-artefact perception using an adaptive combination of noticeable distortions and blurring artefacts.

Video Compression

Perceptually-inspired super-resolution of compressed videos

no code implementations15 Jun 2021 Di Ma, Mariana Afonso, Fan Zhang, David R. Bull

Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency.

Super-Resolution Video Compression

On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation

no code implementations9 Jun 2021 Wei zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.

A Deep Value-network Based Approach for Multi-Driver Order Dispatching

no code implementations8 Jun 2021 Xiaocheng Tang, Zhiwei Qin, Fan Zhang, Zhaodong Wang, Zhe Xu, Yintai Ma, Hongtu Zhu, Jieping Ye

In this work, we propose a deep reinforcement learning based solution for order dispatching and we conduct large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method achieves significant improvement on both total driver income and user experience related metrics.

reinforcement-learning Transfer Learning

Deception Detection in Videos using the Facial Action Coding System

no code implementations28 May 2021 Hammad Ud Din Ahmed, Usama Ijaz Bajwa, Fan Zhang, Muhammad Waqas Anwar

We specifically use long short-term memory (LSTM) which we trained using the real-life trial dataset and it provided one of the best facial only approaches to deception detection.

Deception Detection In Videos Decision Making

Quantitative mapping of the brain's structural connectivity using diffusion MRI tractography: a review

no code implementations23 Apr 2021 Fan Zhang, Alessandro Daducci, Yong He, Simona Schiavi, Caio Seguin, Robert Smith, Chun-Hung Yeh, Tengda Zhao, Lauren J. O'Donnell

Diffusion magnetic resonance imaging (dMRI) tractography is an advanced imaging technique that enables in vivo mapping of the brain's white matter connections at macro scale.

Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection

no code implementations NAACL 2021 Sihao Chen, Fan Zhang, Kazoo Sone, Dan Roth

Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context.

Abstractive Text Summarization

Individually Fair Gradient Boosting

no code implementations ICLR 2021 Alexander Vargo, Fan Zhang, Mikhail Yurochkin, Yuekai Sun

Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern.


Robustifying Conditional Portfolio Decisions via Optimal Transport

1 code implementation30 Mar 2021 Viet Anh Nguyen, Fan Zhang, Jose Blanchet, Erick Delage, Yinyu Ye

Despite the non-linearity of the objective function in the probability measure, we show that the distributionally robust portfolio allocation with side information problem can be reformulated as a finite-dimensional optimization problem.

A Subjective Study on Videos at Various Bit Depths

no code implementations18 Mar 2021 Alex Mackin, Di Ma, Fan Zhang, David Bull

Bit depth adaptation, where the bit depth of a video sequence is reduced before transmission and up-sampled during display, can potentially reduce data rates with limited impact on perceptual quality.

VMAF-based Bitrate Ladder Estimation for Adaptive Streaming

no code implementations12 Mar 2021 Angeliki V. Katsenou, Fan Zhang, Kyle Swanson, Mariana Afonso, Joel Sole, David R. Bull

In HTTP Adaptive Streaming, video content is conventionally encoded by adapting its spatial resolution and quantization level to best match the prevailing network state and display characteristics.


Enhancing VMAF through New Feature Integration and Model Combination

no code implementations10 Mar 2021 Fan Zhang, Angeliki Katsenou, Christos Bampis, Lukas Krasula, Zhi Li, David Bull

VMAF is a machine learning based video quality assessment method, originally designed for streaming applications, which combines multiple quality metrics and video features through SVM regression.

Video Quality Assessment

Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning

no code implementations8 Mar 2021 Yan Jiao, Xiaocheng Tang, Zhiwei Qin, Shuaiji Li, Fan Zhang, Hongtu Zhu, Jieping Ye

We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms.


Three-dimensional charge density wave and robust zero-bias conductance peak inside the superconducting vortex core of a kagome superconductor CsV$_3$Sb$_5$

no code implementations8 Mar 2021 Zuowei Liang, Xingyuan Hou, Wanru Ma, Fan Zhang, Ping Wu, Zongyuan Zhang, Fanghang Yu, J. -J. Ying, Kun Jiang, Lei Shan, Zhenyu Wang, X. -H. Chen

The transition-metal-based kagome metals provide a versatile platform for correlated topological phases hosting various electronic instabilities.

Superconductivity Strongly Correlated Electrons

Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases

no code implementations3 Mar 2021 Xiao Huang, Di Zhu, Fan Zhang, Tao Liu, Xiao Li, Lei Zou

The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.

Model Selection

Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation

no code implementations3 Feb 2021 Mingke Xu, Fan Zhang, Xiaodong Cui, Wei zhang

In this paper, we apply multiscale area attention in a deep convolutional neural network to attend emotional characteristics with varied granularities and therefore the classifier can benefit from an ensemble of attentions with different scales.

Data Augmentation Speech Emotion Recognition

Room-Temperature Superconductivity in Boron-Nitrogen Doped Lanthanum Superhydride

no code implementations24 Dec 2020 Yanfeng Ge, Fan Zhang, Russell J. Hemley

Recent theoretical and experimental studies of hydrogen-rich materials at megabar pressures (i. e., >100 GPa) have led to the discovery of very high-temperature superconductivity in these materials.

Superconductivity Materials Science

Two-fluid Modeling of Acoustic Wave Propagation in Gravitationally Stratified Isothermal Media

no code implementations26 Nov 2020 Fan Zhang, Stefaan Poedts, Andrea Lani, Błażej Kuźma, Kris Murawski

In the present numerical simulations, the initial density is specified to reach hydrostatic equilibrium, and as a comparison, chemical equilibrium is also taken into account to provide a density profile that differs from typical hydrostatic equilibrium profiles.

Plasma Physics Solar and Stellar Astrophysics

Hole-Doped Room-Temperature Superconductivity in H$_{3}$S$_{1-x}$Z$_x$ (Z=C, Si)

no code implementations25 Nov 2020 Yanfeng Ge, Fan Zhang, Ranga P. Dias, Russell J. Hemley, Yugui Yao

We examine the effects of the low-level substitution of S atoms by C and Si atoms on the superconductivity of H$_3$S with the $Im\bar{3}m$ structure at megabar pressure.

Superconductivity Materials Science

CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement

1 code implementation18 Nov 2020 Di Ma, Fan Zhang, David R. Bull

We propose a new Generative Adversarial Network for Compressed Video quality Enhancement (CVEGAN).

Video Compression Video Enhancement

Distributionally Robust Local Non-parametric Conditional Estimation

no code implementations NeurIPS 2020 Viet Anh Nguyen, Fan Zhang, Jose Blanchet, Erick Delage, Yinyu Ye

Conditional estimation given specific covariate values (i. e., local conditional estimation or functional estimation) is ubiquitously useful with applications in engineering, social and natural sciences.

A simulation environment for drone cinematography

no code implementations3 Oct 2020 Fan Zhang, David Hall, Tao Xu, Stephen Boyle, David Bull

Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface.

3D Reconstruction

Video Compression with CNN-based Post Processing

no code implementations16 Sep 2020 Fan Zhang, Di Ma, Chen Feng, David R. Bull

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content.

Video Compression

P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions

1 code implementation14 Sep 2020 Wei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability.

PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images

1 code implementation11 Sep 2020 Dongnan Liu, Donghao Zhang, Yang song, Fan Zhang, Lauren O'Donnell, Heng Huang, Mei Chen, Weidong Cai

In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.

Instance Segmentation Semantic Segmentation +1

Joint Bandwidth Allocation and Path Selection in WANs with Path Cardinality Constraints

no code implementations10 Aug 2020 Jinxin Wang, Fan Zhang, Zhonglin Xie, Gong Zhang, Zaiwen Wen

Almost all existing works deal with such a problem using relaxation techniques to transform it to be a convex optimization problem.


Video compression with low complexity CNN-based spatial resolution adaptation

no code implementations29 Jul 2020 Di Ma, Fan Zhang, David R. Bull

It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder.

Super-Resolution Video Compression

MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering

no code implementations14 Jul 2020 Di Ma, Fan Zhang, David R. Bull

Each MFRB extracts features from multiple convolutional layers using dense connections and a multi-level residual learning structure.

Video Compression

MediaPipe Hands: On-device Real-time Hand Tracking

4 code implementations18 Jun 2020 Fan Zhang, Valentin Bazarevsky, Andrey Vakunov, Andrei Tkachenka, George Sung, Chuo-Ling Chang, Matthias Grundmann

We present a real-time on-device hand tracking pipeline that predicts hand skeleton from single RGB camera for AR/VR applications.

BlazePose: On-device Real-time Body Pose tracking

2 code implementations17 Jun 2020 Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang, Matthias Grundmann

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices.

Pose Estimation Pose Tracking +1

Distributional Robust Batch Contextual Bandits

no code implementations10 Jun 2020 Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet

Leveraging this evaluation scheme, we further propose a novel learning algorithm that is able to learn a policy that is robust to adversarial perturbations and unknown covariate shifts with a performance guarantee based on the theory of uniform convergence.

Multi-Armed Bandits

Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification

no code implementations30 May 2020 Fan Zhang, MinChao Yan, Chen Hu, Jun Ni, Fei Ma

In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image.

Classification General Classification +2

Active Fuzzing for Testing and Securing Cyber-Physical Systems

1 code implementation28 May 2020 Yuqi Chen, Bohan Xuan, Christopher M. Poskitt, Jun Sun, Fan Zhang

Cyber-physical systems (CPSs) in critical infrastructure face a pervasive threat from attackers, motivating research into a variety of countermeasures for securing them.

Active Learning

FiberStars: Visual Comparison of Diffusion Tractography Data between Multiple Subjects

1 code implementation16 May 2020 Loraine Franke, Daniel Karl I. Weidele, Fan Zhang, Suheyla Cetin-Karayumak, Steve Pieper, Lauren J. O'Donnell, Yogesh Rathi, Daniel Haehn

Tractography from high-dimensional diffusion magnetic resonance imaging (dMRI) data allows brain's structural connectivity analysis.

Defending Model Inversion and Membership Inference Attacks via Prediction Purification

no code implementations8 May 2020 Ziqi Yang, Bin Shao, Bohan Xuan, Ee-Chien Chang, Fan Zhang

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence scores predicted by the target classifier.

Inference Attack Membership Inference Attack

Encoding in the Dark Grand Challenge: An Overview

no code implementations7 May 2020 Nantheera Anantrasirichai, Fan Zhang, Alexandra Malyugina, Paul Hill, Angeliki Katsenou

In this paper, we present an overview of the proposed challenge, and test state-of-the-art methods that will be part of the benchmark methods at the stage of the participants' deliverable assessment.

Denoising Image Enhancement

TRAKO: Efficient Transmission of Tractography Data for Visualization

1 code implementation26 Apr 2020 Daniel Haehn, Loraine Franke, Fan Zhang, Suheyla Cetin Karayumak, Steve Pieper, Lauren O'Donnell, Yogesh Rathi

Fiber tracking produces large tractography datasets that are tens of gigabytes in size consisting of millions of streamlines.

BVI-DVC: A Training Database for Deep Video Compression

no code implementations30 Mar 2020 Di Ma, Fan Zhang, David R. Bull

Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches.

Video Compression

BVI-CC: A Dataset for Research on Video Compression and Quality Assessment

no code implementations23 Mar 2020 Angeliki V. Katsenou, Fan Zhang, Mariana Afonso, Goce Dimitrov, David R. Bull

The compression efficiency of the codecs was evaluated with commonly used objective quality metrics, and the subjective quality of their reconstructed content was also evaluated through psychophysical experiments.

Video Compression

Efficient Scenario Generation for Heavy-tailed Chance Constrained Optimization

no code implementations6 Feb 2020 Jose Blanchet, Fan Zhang, Bert Zwart

We consider a generic class of chance-constrained optimization problems with heavy-tailed (i. e., power-law type) risk factors.

Optimization and Control Probability

Residual-Recursion Autoencoder for Shape Illustration Images

no code implementations6 Feb 2020 Qianwei Zhou, Peng Tao, Xiaoxin Li, Sheng-Yong Chen, Fan Zhang, Haigen Hu

Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products.

Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation

1 code implementation12 Jan 2020 Lijun Zhao, Jinjing Zhang, Fan Zhang, Anhong Wang, Huihui Bai, Yao Zhao

Most deep image smoothing operators are always trained repetitively when different explicit structure-texture pairs are employed as label images for each algorithm configured with different parameters.

image smoothing

Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks

no code implementations17 Dec 2019 Fan Zhang, Miao Hu

We demonstrated the proposed methods with implementations of a 4-layer CNN on MNIST and ResNet(20, 32, and 56) on CIFAR-10.

Defects Mitigation in Resistive Crossbars for Analog Vector Matrix Multiplication

no code implementations17 Dec 2019 Fan Zhang, Miao Hu

With storage and computation happening at the same place, computing in resistive crossbars minimizes data movement and avoids the memory bottleneck issue.

Hepatocellular Carcinoma Intra-arterial Treatment Response Prediction for Improved Therapeutic Decision-Making

no code implementations1 Dec 2019 Junlin Yang, Nicha C. Dvornek, Fan Zhang, Julius Chapiro, MingDe Lin, Aaron Abajian, James S. Duncan

This work proposes a pipeline to predict treatment response to intra-arterial therapy of patients with Hepatocellular Carcinoma (HCC) for improved therapeutic decision-making.

Decision Making

Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set

no code implementations18 Nov 2019 Fan Zhang, Hao Wang, Jiashan Wang, Kai Yang

In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint.

ViSTRA2: Video Coding using Spatial Resolution and Effective Bit Depth Adaptation

no code implementations7 Nov 2019 Fan Zhang, Mariana Afonso, David R. Bull

Our results show consistent and significant compression gains against HM and VVC based on Bj{\o}negaard Delta measurements, with average BD-rate savings of 12. 6% (PSNR) and 19. 5% (VMAF) over HM and 5. 5% (PSNR) and 8. 6% (VMAF) over VTM.

Video Compression

ACFNet: Attentional Class Feature Network for Semantic Segmentation

1 code implementation ICCV 2019 Fan Zhang, Yanqin Chen, Zhihang Li, Zhibin Hong, Jingtuo Liu, Feifei Ma, Junyu Han, Errui Ding

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective.

Semantic Segmentation

Edge AIBench: Towards Comprehensive End-to-end Edge Computing Benchmarking

no code implementations6 Aug 2019 Tianshu Hao, Yunyou Huang, Xu Wen, Wanling Gao, Fan Zhang, Chen Zheng, Lei Wang, Hainan Ye, Kai Hwang, Zujie Ren, Jianfeng Zhan

In edge computing scenarios, the distribution of data and collaboration of workloads on different layers are serious concerns for performance, privacy, and security issues.

Performance Distributed, Parallel, and Cluster Computing

A Survey of Deep Learning-based Object Detection

no code implementations11 Jul 2019 Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhixi Feng, Rong Qu

Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in peoples life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class.

Autonomous Driving Object Detection

Predicting Treatment Initiation from Clinical Time Series Data via Graph-Augmented Time-Sensitive Model

no code implementations1 Jul 2019 Fan Zhang, Tong Wu, Yunlong Wang, Yong Cai, Cao Xiao, Emily Zhao, Lucas Glass, Jimeng Sun

Many computational models were proposed to extract temporal patterns from clinical time series for each patient and among patient group for predictive healthcare.

Time Series

MediaPipe: A Framework for Building Perception Pipelines

2 code implementations14 Jun 2019 Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Guang Yong, Juhyun Lee, Wan-Teh Chang, Wei Hua, Manfred Georg, Matthias Grundmann

A developer can use MediaPipe to build prototypes by combining existing perception components, to advance them to polished cross-platform applications and measure system performance and resource consumption on target platforms.

Distributed, Parallel, and Cluster Computing

A Distributionally Robust Boosting Algorithm

no code implementations20 May 2019 Jose Blanchet, Yang Kang, Fan Zhang, Zhangyi Hu

Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation.

Decision Making Decision Making Under Uncertainty

Noise-Tolerant Paradigm for Training Face Recognition CNNs

2 code implementations CVPR 2019 Wei Hu, Yangyu Huang, Fan Zhang, Ruirui Li

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR).

Face Recognition

Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations

no code implementations22 Jan 2019 Zhoutong Wang, Qianhui Liang, Fabio Duarte, Fan Zhang, Louis Charron, Lenna Johnsen, Bill Cai, Carlo Ratti

Evaluating legibility is particularly desirable in indoor spaces, since it has a large impact on human behavior and the efficiency of space utilization.

Nonconvex and Nonsmooth Sparse Optimization via Adaptively Iterative Reweighted Methods

no code implementations24 Oct 2018 Hao Wang, Fan Zhang, Yuanming Shi, Yaohua Hu

We propose a general formulation of nonconvex and nonsmooth sparse optimization problems with convex set constraint, which can take into account most existing types of nonconvex sparsity-inducing terms, bringing strong applicability to a wide range of applications.

Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes

1 code implementation4 Oct 2018 Jose Blanchet, Karthyek Murthy, Fan Zhang

We consider optimal transport based distributionally robust optimization (DRO) problems with locally strongly convex transport cost functions and affine decision rules.

Optimization and Control Primary: 90C15, Secondary: 65K05, 90C47

Memristor-based Deep Convolution Neural Network: A Case Study

no code implementations14 Sep 2018 Fan Zhang, Miao Hu

In this paper, we firstly introduce a method to efficiently implement large-scale high-dimensional convolution with realistic memristor-based circuit components.

High-speed Tracking with Multi-kernel Correlation Filters

no code implementations CVPR 2018 Ming Tang, Bin Yu, Fan Zhang, Jinqiao Wang

In this paper, we will introduce the MKL into KCF in a different way than MKCF.

TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation

no code implementations29 Apr 2018 Kai Yue, Lei Yang, Ruirui Li, Wei Hu, Fan Zhang, Wei Li

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.

Semantic Segmentation

SeqFace: Make full use of sequence information for face recognition

1 code implementation17 Mar 2018 Wei Hu, Yangyu Huang, Fan Zhang, Ruirui Li, Wei Li, Guodong Yuan

Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.

Face Recognition Face Verification

Parameter-free $\ell_p$-Box Decoding of LDPC Codes

1 code implementation29 Nov 2017 Qiong Wu, Fan Zhang, Hao Wang, Jun Lin, Yang Liu

The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.

Information Theory Information Theory

SAR Target Recognition Using the Multi-aspect-aware Bidirectional LSTM Recurrent Neural Networks

no code implementations25 Jul 2017 Fan Zhang, Chen Hu, Qiang Yin, Wei Li, Heng-Chao Li, Wen Hong

However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information.

Dimensionality Reduction

Data-driven Optimal Cost Selection for Distributionally Robust Optimization

no code implementations19 May 2017 Jose Blanchet, Yang Kang, Fan Zhang, Karthyek Murthy

Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems.

Doubly Robust Data-Driven Distributionally Robust Optimization

no code implementations19 May 2017 Jose Blanchet, Yang Kang, Fan Zhang, Fei He, Zhangyi Hu

Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms.

A Joint Identification Approach for Argumentative Writing Revisions

no code implementations28 Feb 2017 Fan Zhang, Diane Litman

This paper proposes an approach that identifies the revision location and the revision type jointly to solve the issue of error propagation.

Classification General Classification

A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data

no code implementations26 Feb 2017 Fan Zhang, Bo Du, Liangpei Zhang

For the second target, a novel CNN-based universal framework is proposed to process the VHR satellite images and generate the land-use, urban density, and population distribution maps.

Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification

no code implementations COLING 2016 Fan Zhang, Diane Litman, Katherine Forbes Riley

Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts.

Classification General Classification

A global optimization algorithm for sparse mixed membership matrix factorization

no code implementations19 Oct 2016 Fan Zhang, Chuangqi Wang, Andrew Trapp, Patrick Flaherty

Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity.

Indoor Space Recognition using Deep Convolutional Neural Network: A Case Study at MIT Campus

no code implementations7 Oct 2016 Fan Zhang, Fabio Duarte, Ruixian Ma, Dimitrios Milioris, Hui Lin, Carlo Ratti

In this paper, we propose a robust and parsimonious approach using Deep Convolutional Neural Network (DCNN) to recognize and interpret interior space.

Scene Recognition

Stealing Machine Learning Models via Prediction APIs

1 code implementation9 Sep 2016 Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, Thomas Ristenpart

In such attacks, an adversary with black-box access, but no prior knowledge of an ML model's parameters or training data, aims to duplicate the functionality of (i. e., "steal") the model.

Learning Theory Model extraction

Casual Stereoscopic Panorama Stitching

no code implementations CVPR 2015 Fan Zhang, Feng Liu

The stitching of the right views is formulated as a labeling problem that is constrained by the stitching of the left views to make the left- and right-view panorama consistent to avoid retinal rivalry.

Image Stitching

Parallax-tolerant Image Stitching

no code implementations CVPR 2014 Fan Zhang, Feng Liu

We then pre-align input images using the optimal homography and further use content-preserving warping to locally refine the alignment.

Image Stitching Local Distortion

Real-time Decolorization using Dominant Colors

no code implementations10 Apr 2014 Wei Hu, Wei Li, Fan Zhang, Qian Du

Decolorization is the process to convert a color image or video to its grayscale version, and it has received great attention in recent years.

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