Search Results for author: Wei Jiang

Found 64 papers, 16 papers with code

Facke: a Survey on Generative Models for Face Swapping

1 code implementation22 Jun 2022 Wei Jiang, Wentao Dong

In this work, we investigate into the performance of mainstream neural generative models on the very task of swapping faces.

Face Swapping

Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction

no code implementations CVPR 2022 Zhihao Hu, Guo Lu, Jinyang Guo, Shan Liu, Wei Jiang, Dong Xu

The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H. 264/H. 265 for both motion and residual compression.

Motion Compensation Motion Estimation +1

Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor

no code implementations2 May 2022 Lijun Zhang, Wei Jiang, JinFeng Yi, Tianbao Yang

In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost.

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

no code implementations11 Apr 2022 Haojie Liu, Daoxun Xia, Wei Jiang, Chao Xu

In order to mitigate the impact of large modality discrepancy existing in heterogeneous images, previous methods attempt to apply generative adversarial network (GAN) to generate the modality-consisitent data.

Person Re-Identification

NeuMan: Neural Human Radiance Field from a Single Video

no code implementations23 Mar 2022 Wei Jiang, Kwang Moo Yi, Golnoosh Samei, Oncel Tuzel, Anurag Ranjan

Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences.

Optimal Algorithms for Stochastic Multi-Level Compositional Optimization

no code implementations15 Feb 2022 Wei Jiang, Bokun Wang, Yibo Wang, Lijun Zhang, Tianbao Yang

To address this limitation, we propose a Stochastic Multi-level Variance Reduction method (SMVR), which achieves the optimal sample complexity of $\mathcal{O}\left(1 / \epsilon^{3}\right)$ to find an $\epsilon$-stationary point for non-convex objectives.

Vertical Federated Edge Learning with Distributed Integrated Sensing and Communication

no code implementations21 Jan 2022 Peixi Liu, Guangxu Zhu, Wei Jiang, Wu Luo, Jie Xu, Shuguang Cui

This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC).

LSVC: A Learning-Based Stereo Video Compression Framework

no code implementations CVPR 2022 Zhenghao Chen, Guo Lu, Zhihao Hu, Shan Liu, Wei Jiang, Dong Xu

In this work, we propose the first end-to-end optimized framework for compressing automotive stereo videos (i. e., stereo videos from autonomous driving applications) from both left and right views.

Autonomous Driving Motion Compensation +1

Fast Data-Driven Adaptation of Radar Detection via Meta-Learning

no code implementations3 Dec 2021 Wei Jiang, Alexander M. Haimovich, Mark Govoni, Timothy Garner, Osvaldo Simeone

One approach is based on transfer learning: it first pre-trains a detector such that it works well on data collected in previously observed environments, and then it adapts the pre-trained detector to the specific current environment.

Meta-Learning Transfer Learning

Online Meta Adaptation for Variable-Rate Learned Image Compression

no code implementations16 Nov 2021 Wei Jiang, Wei Wang, Songnan Li, Shan Liu

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.

Image Compression Meta-Learning +2

A Two-stage Pricing Strategy Considering Learning Effects and Word-of-Mouth

no code implementations22 Oct 2021 YanRong Li, Lai Wei, Wei Jiang

This paper proposes a two-stage pricing strategy for nondurable (such as typical electronics) products, where retail price is cut down at certain time points of the product lifecycle.

Reinforcement Learning for Process Control with Application in Semiconductor Manufacturing

no code implementations22 Oct 2021 YanRong Li, Juan Du, Wei Jiang

Process control is widely discussed in the manufacturing process, especially for semiconductor manufacturing.


A Survey of Knowledge Enhanced Pre-trained Models

no code implementations1 Oct 2021 Jian Yang, Gang Xiao, Yulong Shen, Wei Jiang, Xinyu Hu, Ying Zhang, Jinghui Peng

Pre-trained models learn informative representations on large-scale training data through a self-supervised or supervised learning method, which has achieved promising performance in natural language processing (NLP), computer vision (CV), and cross-modal fields after fine-tuning.

Computer Vision Natural Language Processing +2

Machine learning based iterative learning control for non-repetitive time-varying systems

no code implementations1 Jul 2021 Yiyang Chen, Wei Jiang, Themistoklis Charalambous

A machine learning (ML) based nominal model update mechanism, which utilizes the linear regression technique to update the nominal model at each ILC trial only using the current trial information, is proposed for non-repetitive TVSs in order to enhance the ILC performance.

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression

no code implementations15 Jun 2021 Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.

Neural Network Compression

Substitutional Neural Image Compression

no code implementations16 May 2021 Xiao Wang, Wei Jiang, Wei Wang, Shan Liu, Brian Kulis, Peter Chin

The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.

Image Compression

Multi-agent consensus with heterogeneous time-varying input and communication delays in digraphs

no code implementations3 May 2021 Wei Jiang, Kun Liu, Themistoklis Charalambous

First, for all agents whose state matrix has no eigenvalues with positive real parts, a communication-delay-related observer, which is used to construct the controller, is designed for followers to estimate the leader's state information.

An Iteratively Reweighted Method for Sparse Optimization on Nonconvex $\ell_{p}$ Ball

no code implementations7 Apr 2021 Hao Wang, Xiangyu Yang, Wei Jiang

Specifically, if the current iterate is in the interior of the feasible set, then the weighted $\ell_{1}$ ball is formed by linearizing the $\ell_{p}$ norm at the current iterate.

COTR: Correspondence Transformer for Matching Across Images

1 code implementation ICCV 2021 Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi

We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.

Dense Pixel Correspondence Estimation Optical Flow Estimation

Revisiting Smoothed Online Learning

no code implementations NeurIPS 2021 Lijun Zhang, Wei Jiang, Shiyin Lu, Tianbao Yang

Moreover, when the hitting cost is both convex and $\lambda$-quadratic growth, we reduce the competitive ratio to $1 + \frac{2}{\sqrt{\lambda}}$ by minimizing the weighted sum of the hitting cost and the switching cost.

online learning

Predictive Relay Selection: A Cooperative Diversity Scheme Using Deep Learning

no code implementations5 Feb 2021 Wei Jiang, Hans Dieter Schotten

In this paper, we propose a novel cooperative multi-relay transmission scheme for mobile terminals to exploit spatial diversity.

Information Theory Signal Processing Information Theory

A Simple Cooperative Diversity Method Based on Deep-Learning-Aided Relay Selection

no code implementations5 Feb 2021 Wei Jiang, Hans Dieter Schotten

Opportunistic relay selection (ORS) has been recognized as a simple but efficient method for mobile nodes to achieve cooperative diversity in slow fading channels.

The Road Towards 6G: A Comprehensive Survey

no code implementations2 Feb 2021 Wei Jiang, Bin Han, Mohammad Asif Habibi, Hans Dieter Schotten

As of today, the fifth generation (5G) mobile communication system has been rolled out in many countries and the number of 5G subscribers already reaches a very large scale.

Implementation of OpenAirInterface-based real-world channel measurement for evaluating wireless transmission algorithms

no code implementations11 Jan 2021 Qiuheng Zhou, Wei Jiang

The results from the measurement are then trained and tested on the channel prediction algorithm.

An Abstracted Survey on 6G: Drivers, Requirements, Efforts, and Enablers

no code implementations4 Jan 2021 Bin Han, Wei Jiang, Mohammad Asif Habibi, Hans D. Schotten

As of today, 5G mobile systems have been already widely rolled out, it is the right time for academia and industry to explore the next generation mobile communication system beyond 5G.

Networking and Internet Architecture

1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification

1 code implementation25 Dec 2020 Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang

Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.

Domain Adaptation

A pipeline for fair comparison of graph neural networks in node classification tasks

1 code implementation19 Dec 2020 Wentao Zhao, Dalin Zhou, Xinguo Qiu, Wei Jiang

We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification.

Benchmark Data Augmentation +2

DeRF: Decomposed Radiance Fields

no code implementations CVPR 2021 Daniel Rebain, Wei Jiang, Soroosh Yazdani, Ke Li, Kwang Moo Yi, Andrea Tagliasacchi

Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering.

ArchNet: Data Hiding Model in Distributed Machine Learning System

no code implementations23 Apr 2020 Kaiyan Chang, Wei Jiang, Jinyu Zhan, Zicheng Gong, Weijia Pan

Specifically, our design can improve the accuracy on MNIST up to 97. 26% compared with RC4. The accuracies on the datasets encrypted by ArchNet are 97. 26%, 84. 15% and 79. 80%, and they are 97. 31%, 82. 31% and 80. 22% on the original datasets, which shows that the encrypted accuracy of ArchNet has the same performance as the base model.

Image Classification

Survey of Privacy-Preserving Collaborative Filtering

no code implementations18 Mar 2020 Islam Elnabarawy, Wei Jiang, Donald C. Wunsch II

Collaborative filtering recommendation systems provide recommendations to users based on their own past preferences, as well as those of other users who share similar interests.

Collaborative Filtering Privacy Preserving +1

Improving Uyghur ASR systems with decoders using morpheme-based language models

no code implementations3 Mar 2020 Zicheng Qiu, Wei Jiang, Turghunjan Mamut

The experimental results show that the decoding based on the static and fully composed graph reduces state-of-the-art Word Error Rate (WER) on the clean and noiseless speech test task in THUYG-20 to 14. 24%.

Automatic Speech Recognition speech-recognition

Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

no code implementations29 Feb 2020 Xing Fan, Hao Luo, Chi Zhang, Wei Jiang

Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.

Computer Vision Cross-Modality Person Re-identification +2

End-to-end Learning of Waveform Generation and Detection for Radar Systems

no code implementations2 Dec 2019 Wei Jiang, Alexander M. Haimovich, Osvaldo Simeone

An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system.

Signal Processing

SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT

no code implementations CONLL 2019 Yue Zhang, Wei Jiang, Qingrong Xia, Junjie Cao, Rui Wang, Zhenghua Li, Min Zhang

Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.

Multi-Task Learning POS

Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification

no code implementations12 Oct 2019 Jingjing Qian, Wei Jiang, Hao Luo, Hongyan Yu

Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security.

Computer Vision Vehicle Re-Identification

Optimizing Through Learned Errors for Accurate Sports Field Registration

1 code implementation17 Sep 2019 Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles, Weiwei Sun, Mehrsan Javan, Kwang Moo Yi

We propose an optimization-based framework to register sports field templates onto broadcast videos.

Adaptive Bayesian SLOPE -- High-dimensional Model Selection with Missing Values

2 code implementations14 Sep 2019 Wei Jiang, Malgorzata Bogdan, Julie Josse, Blazej Miasojedow, Veronika Rockova, Traumabase group

We consider the problem of variable selection in high-dimensional settings with missing observations among the covariates.

Methodology Applications Computation

Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency

no code implementations19 Jun 2019 Zaiqiang Wu, Wei Jiang

The experimental results also show that the proposed differentiable renderer is of higher accuracy and efficiency compared with previous method of differentiable renderer.

3D Pose Estimation 3D Reconstruction

HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing

no code implementations SEMEVAL 2019 Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang

The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.

General Classification Multi-Task Learning +1

A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation

no code implementations21 May 2019 Wei Jiang, Yan Tang

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network.

Chinese Word Segmentation

ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views

1 code implementation25 Mar 2019 Chongsheng Zhang, Guowen Peng, Yuefeng Tao, Feifei Fu, Wei Jiang, George Almpanidis, Ke Chen

Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.

Scene Text Detection

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

7 code implementations17 Mar 2019 Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, Wei Jiang

In the literature, some effective training tricks are briefly appeared in several papers or source codes.

Person Re-Identification

STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

no code implementations17 Mar 2019 Hao Luo, Xing Fan, Chi Zhang, Wei Jiang

Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.

Person Re-Identification

An End-to-End Network for Panoptic Segmentation

no code implementations CVPR 2019 Huanyu Liu, Chao Peng, Changqian Yu, Jingbo Wang, Xu Liu, Gang Yu, Wei Jiang

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic.

Benchmark Panoptic Segmentation

HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing

no code implementations11 Mar 2019 Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang

The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.

General Classification UCCA Parsing

Improve Object Detection by Data Enhancement based on Generative Adversarial Nets

no code implementations5 Mar 2019 Wei Jiang, Na Ying

The accuracy of the object detection model depends on whether the anchor boxes effectively trained.

object-detection Object Detection

A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation

no code implementations24 Jan 2019 Zaiqiang Wu, Wei Jiang, Hao Luo, Lin Cheng

To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection.

3D Pose Estimation 3D Reconstruction

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

no code implementations16 Oct 2018 Xing Fan, Hao Luo, Xuan Zhang, Lingxiao He, Chi Zhang, Wei Jiang

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.

Person Re-Identification

Distributing and Obfuscating Firewalls via Oblivious Bloom Filter Evaluation

no code implementations3 Oct 2018 Ken Goss, Wei Jiang

In this paper, we develop an innovative distributed architecture to obliviously manage and evaluate firewalls to prevent both insider and external attacks oriented to the firewalls.

Cryptography and Security

SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

2 code implementations2 Jul 2018 Xing Fan, Wei Jiang, Hao Luo, Mengjuan Fei

In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.

Person Re-Identification Re-Ranking

DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block

no code implementations11 Jun 2018 Wei Jiang, Yan Wu

We propose the DFNet and make two main contributions, one is dynamic loss weights, and the other is residual fusion block (RFB).

Semantic Segmentation

Stochastic Approximation EM for Logistic Regression with Missing Values

2 code implementations11 May 2018 Wei Jiang, Julie Josse, Marc Lavielle, Traumabase group

We propose a complete approach, including the estimation of parameters and their variance, derivation of confidence intervals, a model selection procedure, and a method for prediction on test sets with missing values.


VH-HFCN based Parking Slot and Lane Markings Segmentation on Panoramic Surround View

no code implementations19 Apr 2018 Yan Wu, Tao Yang, Junqiao Zhao, Linting Guan, Wei Jiang

At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset.

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

6 code implementations22 Nov 2017 Xuan Zhang, Hao Luo, Xing Fan, Weilai Xiang, Yixiao Sun, Qiqi Xiao, Wei Jiang, Chi Zhang, Jian Sun

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.

Person Re-Identification

A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets

no code implementations11 May 2017 Thangarajah Akilan, Q. M. Jonathan Wu, Wei Jiang

Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area.

Action Classification Classification +3

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