Search Results for author: Jun Liu

Found 130 papers, 20 papers with code

OID: Outlier Identifying and Discarding in Blind Image Deblurring

no code implementations ECCV 2020 Liang Chen, Faming Fang, Jiawei Zhang, Jun Liu, Guixu Zhang

Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.

Blind Image Deblurring Image Deblurring

Learning Progressive Joint Propagation for Human Motion Prediction

no code implementations ECCV 2020 Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu, Nadia Magnenat Thalmann

Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.

Human motion prediction motion prediction

Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation

no code implementations ECCV 2020 Zhipeng Fan, Jun Liu, Yao Wang

A novel model, called Adaptive Computationally Efficient (ACE) network, is proposed, which takes advantage of a Gaussian kernel based Gate Module to dynamically switch the computation between a light model and a heavy network for feature extraction.

3D Hand Pose Estimation

Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis

no code implementations ECCV 2020 Siyuan Yang, Jun Liu, Shijian Lu, Meng Hwa Er, Alex C. Kot

The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features and models.

3D Hand Pose Estimation Gesture Recognition

HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction

no code implementations ECCV 2020 Tianjiao Li, Jun Liu, Wei zhang, Ling-Yu Duan

In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.

Activity Prediction Skeleton Based Action Recognition

Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning

no code implementations17 Oct 2021 Yudai Pan, Jun Liu, Lingling Zhang, Xin Hu, Tianzhe Zhao, Qika Lin

Relation reasoning in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm is learning the embeddings of relations and entities, which is limited to a transductive setting and has restriction on processing unseen entities in an inductive situation.

Knowledge Graphs

Recent Advances of Continual Learning in Computer Vision: An Overview

no code implementations23 Sep 2021 Haoxuan Qu, Hossein Rahmani, Li Xu, Bryan Williams, Jun Liu

In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order.

Continual Learning Knowledge Distillation

Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation

no code implementations8 Sep 2021 Geng-Xin Xu, Chen Liu, Jun Liu, Zhongxiang Ding, Feng Shi, Man Guo, Wei Zhao, Xiaoming Li, Ying WEI, Yaozong Gao, Chuan-Xian Ren, Dinggang Shen

Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.

Computed Tomography (CT) Domain Adaptation +1

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

no code implementations4 Sep 2021 Chenjie Wang, Chengyuan Li, Bin Luo, Wei Wang, Jun Liu

Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet.

Instance Segmentation Semantic Segmentation

Learning Inner-Group Relations on Point Clouds

1 code implementation ICCV 2021 Haoxi Ran, Wei Zhuo, Jun Liu, Li Lu

We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation.

3D Classification 3D Point Cloud Classification +2

Seirios: Leveraging Multiple Channels for LoRaWAN Indoor and Outdoor Localization

no code implementations16 Aug 2021 Jun Liu, Jiayao Gao, Sanjay Jha, Wen Hu

By exploiting both the original and the conjugate of the physical layer, Seirios can resolve the direct path from multiple reflectors in both indoor and outdoor environments.


Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

1 code implementation6 Aug 2021 Yan Bai, Jile Jiao, Shengsen Wu, Yihang Lou, Jun Liu, Xuetao Feng, Ling-Yu Duan

It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database.

Global Optimization

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

no code implementations5 Aug 2021 Duo Peng, Yinjie Lei, Lingqiao Liu, Pingping Zhang, Jun Liu

In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS.

Domain Generalization Semantic Segmentation

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

3 code implementations ICCV 2021 Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan

To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.

Domain Adaptive Person Re-Identification Person Re-Identification

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

no code implementations ICCV 2021 Siyuan Yang, Jun Liu, Shijian Lu, Meng Hwa Er, Alex C. Kot

We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data.

3D Action Recognition Colorization +1

DeceFL: A Principled Decentralized Federated Learning Framework

1 code implementation15 Jul 2021 Ye Yuan, Jun Liu, Dou Jin, Zuogong Yue, Ruijuan Chen, Maolin Wang, Chuan Sun, Lei Xu, Feng Hua, Xin He, Xinlei Yi, Tao Yang, Hai-Tao Zhang, Shaochun Sui, Han Ding

Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.

Federated Learning

A Low Complexity Learning-based Channel Estimation for OFDM Systems with Online Training

no code implementations14 Jul 2021 Kai Mei, Jun Liu, Xiaoying Zhang, Kuo Cao, Nandana Rajatheva, Jibo Wei

Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission.

Resilient UAV Swarm Communications with Graph Convolutional Neural Network

1 code implementation30 Jun 2021 Zhiyu Mou, Feifei Gao, Jun Liu, Qihui Wu

Numerical results show that the proposed algorithms can rebuild the communication connectivity of the USNET more quickly than the existing algorithms under both one-off UEDs and general UEDs.

Meta-Learning Trajectory Planning

Interventional Video Grounding with Dual Contrastive Learning

1 code implementation CVPR 2021 Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu

2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.

Causal Inference Contrastive Learning +1

QFCNN: Quantum Fourier Convolutional Neural Network

no code implementations19 Jun 2021 Feihong Shen, Jun Liu

The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers.

Image Classification Traffic Prediction

Conterfactual Generative Zero-Shot Semantic Segmentation

no code implementations11 Jun 2021 Feihong Shen, Jun Liu, Ping Hu

In this work, we consider counterfactual methods to avoid the confounder in the original model.

Causal Inference Semantic Segmentation +1

Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition

no code implementations7 Jun 2021 XiaoHong Wang, Xudong Jiang, Henghui Ding, Yuqian Zhao, Jun Liu

In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i. e., skin lesion segmentation and melanoma recognition.

Lesion Segmentation

Opening the Black Box of Deep Neural Networks in Physical Layer Communication

no code implementations2 Jun 2021 Jun Liu, Kai Mei, Dongtang Ma, Jibo Wei

Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems.

Generalizable Person Re-identification with Relevance-aware Mixture of Experts

no code implementations CVPR 2021 Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan

Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.

Generalizable Person Re-identification

Safety-Critical Control of Stochastic Systems using Stochastic Control Barrier Functions

no code implementations6 Apr 2021 Chuanzheng Wang, Yiming Meng, Stephen L. Smith, Jun Liu

We propose a notion of stochastic control barrier functions (SCBFs)and show that SCBFs can significantly reduce the control efforts, especially in the presence of noise, compared to stochastic reciprocal control barrier functions (SRCBFs), and offer a less conservative estimation of safety probability, compared to stochastic zeroing control barrier functions (SZCBFs).

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

no code implementations3 Apr 2021 Yinan Li, Zhibing Sun, Jun Liu

We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic B\"uchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances.

Motion Planning Temporal Logic

UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

1 code implementation CVPR 2021 Tianjiao Li, Jun Liu, Wei zhang, Yun Ni, Wenqian Wang, Zhiheng Li

Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models.

Action Recognition Pedestrian Attribute Recognition +2

Rank-One Prior: Toward Real-Time Scene Recovery

no code implementations CVPR 2021 Jun Liu, Ryan Wen Liu, Jianing Sun, Tieyong Zeng

To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze.

Autonomous Vehicles

SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events

1 code implementation CVPR 2021 Li Xu, He Huang, Jun Liu

In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10, 080 in-the-wild videos and annotated 62, 535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.

Autonomous Vehicles Causal Inference +3

Constrained Radar Waveform Design for Range Profiling

no code implementations18 Mar 2021 Bo Tang, Jun Liu, Hai Wang, Yihua Hu

Range profiling refers to the measurement of target response along the radar slant range.

RL-CSDia: Representation Learning of Computer Science Diagrams

no code implementations10 Mar 2021 Shaowei Wang, Lingling Zhang, Xuan Luo, Yi Yang, Xin Hu, Jun Liu

Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank.

Question Answering Representation Learning +1

Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing

no code implementations ICCV 2021 Henghui Ding, HUI ZHANG, Jun Liu, Jiaxin Li, Zijian Feng, Xudong Jiang

In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions.

Scene Parsing

Motion Adaptive Pose Estimation From Compressed Videos

no code implementations ICCV 2021 Zhipeng Fan, Jun Liu, Yao Wang

A novel model, called Motion Adaptive Pose Net is proposed to exploit the compressed streams to efficiently decode pose sequences from videos.

Motion Compensation Pose Estimation

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

no code implementations ICCV 2021 Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu, Nadia Magnenat Thalmann

Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series.

motion prediction motion synthesis

Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

1 code implementation26 Dec 2020 Yongxing Dai, Jun Liu, Yan Bai, Zekun Tong, Ling-Yu Duan

To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.

Domain Adaptive Person Re-Identification Person Re-Identification

Human Action Recognition from Various Data Modalities: A Review

no code implementations22 Dec 2020 Zehua Sun, Qiuhong Ke, Hossein Rahmani, Mohammed Bennamoun, Gang Wang, Jun Liu

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action.

Action Recognition

Object Detection based on OcSaFPN in Aerial Images with Noise

no code implementations18 Dec 2020 Chengyuan Li, Jun Liu, Hailong Hong, Wenju Mao, Chenjie Wang, Chudi Hu, Xin Su, Bin Luo

On the basis of this, a novel octave convolution-based semantic attention feature pyramid network (OcSaFPN) is proposed to get higher accuracy in object detection with noise.

Denoising Object Detection

A ROM-accelerated parallel-in-time preconditioner for solving all-at-once systems from evolutionary PDEs

no code implementations16 Dec 2020 Jun Liu, Zhu Wang

In this paper we propose to use model reduction techniques for speeding up the diagonalization-based parallel-in-time (ParaDIAG) preconditioner, for iteratively solving all-at-once systems from evolutionary PDEs.

Numerical Analysis Numerical Analysis Dynamical Systems

XTQA: Span-Level Explanations of the Textbook Question Answering

1 code implementation25 Nov 2020 Jie Ma, Jun Liu, Junjun Li, Qinghua Zheng, Qingyu Yin, Jianlong Zhou, Yi Huang

Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.

Question Answering

Skeleton-based Relational Reasoning for Group Activity Analysis

no code implementations11 Nov 2020 Mauricio Perez, Jun Liu, Alex C. Kot

In this paper, we leverage the skeleton information to learn the interactions between the individuals straight from it.

Group Activity Recognition Optical Flow Estimation +1

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-ray Images

1 code implementation11 Nov 2020 Jingxiong Li, Yaqi Wang, Shuai Wang, Jun Wang, Jun Liu, Qun Jin, Lingling Sun

Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models.

Classification COVID-19 Diagnosis +1

Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR

no code implementations9 Nov 2020 Xiaohui Zhang, Frank Zhang, Chunxi Liu, Kjell Schubert, Julian Chan, Pradyot Prakash, Jun Liu, Ching-Feng Yeh, Fuchun Peng, Yatharth Saraf, Geoffrey Zweig

In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.

automatic-speech-recognition Speech Recognition

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications

no code implementations9 Nov 2020 Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu

Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.

Indoor Localization Monocular Depth Estimation +1

Exact Phase Transitions of Model RB with Slower-Growing Domains

no code implementations5 Nov 2020 Jun Liu, Ke Xu, Guangyan Zhou

The second moment method has always been an effective tool to lower bound the satisfiability threshold of many random constraint satisfaction problems.

Robust Face Alignment by Multi-order High-precision Hourglass Network

no code implementations17 Oct 2020 Jun Wan, Zhihui Lai, Jun Liu, Jie zhou, Can Gao

Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments.

Face Alignment Robust Face Alignment

Novel Parameter Estimation and Radar Detection Approaches for Multiple Point-like Targets: Designs and Comparisons

no code implementations17 Sep 2020 Pia Addabbo, Jun Liu, Danilo Orlando, Giuseppe Ricci

In this work, we develop and compare two innovative strategies for parameter estimation and radar detection of multiple point-like targets.

Radar Adaptive Detection Architectures for Heterogeneous Environments

no code implementations4 Aug 2020 Jun Liu, Davide Massaro, Danilo Orlando, Alfonso Farina

In this paper, four adaptive radar architectures for target detection in heterogeneous Gaussian environments are devised.

Improving probability selecting based weights for Satisfiability Problem

no code implementations30 Jul 2020 Huimin Fu, Yang Xu, Jun Liu, Guanfeng Wu, Sutcliffe Geoff

SelectNTS is an improved probability selecting based local search algorithm for SAT problem.

Variable Selection

On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts

no code implementations21 Jul 2020 Jun Liu

A basic simulation-based reinforcement learning algorithm is the Monte Carlo Exploring States (MCES) method, also known as optimistic policy iteration, in which the value function is approximated by simulated returns and a greedy policy is selected at each iteration.

Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach

no code implementations17 Jul 2020 Jun Liu, Kai Mei, Xiaochen Zhang, Des McLernon, Dongtang Ma, Jibo Wei, Syed Ali Raza Zaidi

Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency synchronization significantly impacts the overall system performance.

Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet

1 code implementation29 Jun 2020 Chuang Zhu, Ke Mei, Ting Peng, Yihao Luo, Jun Liu, Ying Wang, Mulan Jin

The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate.

MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation

no code implementations27 Jun 2020 Jun Liu, Qing Li, Rui Cao, Wenming Tang, Guoping Qiu

To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices.

Monocular Depth Estimation

Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?

no code implementations9 Jun 2020 Weixing Liu, Jun Liu, Bin Luo

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually.

Object Detection

KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis

1 code implementation29 May 2020 Filip Ilievski, Daniel Garijo, Hans Chalupsky, Naren Teja Divvala, Yixiang Yao, Craig Rogers, Rongpeng Li, Jun Liu, Amandeep Singh, Daniel Schwabe, Pedro Szekely

Knowledge graphs (KGs) have become the preferred technology for representing, sharing and adding knowledge to modern AI applications.

Knowledge Graphs

DeepSSM: Deep State-Space Model for 3D Human Motion Prediction

no code implementations25 May 2020 Xiaoli Liu, Jianqin Yin, Huaping Liu, Jun Liu

Moreover, a novel deep network is designed to build this system, enabling us to utilize both the advantages of deep network and state-space model.

Human motion prediction motion prediction

ParaDiag: parallel-in-time algorithms based on the diagonalization technique

1 code implementation19 May 2020 Martin J. Gander, Jun Liu, Shu-Lin Wu, Xiaoqiang Yue, Tao Zhou

These results are obtained on the Tianhe-1 supercomputer in China and the SIUE Campus Cluster in the US and and we compare these results to the performance of parareal and MGRiT, two widely used PinT algorithms.

Numerical Analysis Numerical Analysis

Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation

no code implementations15 May 2020 Jun Liu, Xue-Cheng Tai, Shousheng Luo

This method is flexible and it can handle multiple objects and allow some of the objects to be convex.

Semantic Segmentation

Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images

no code implementations8 May 2020 Kelei He, Wei Zhao, Xingzhi Xie, Wen Ji, Mingxia Liu, Zhenyu Tang, Feng Shi, Yang Gao, Jun Liu, Junfeng Zhang, Dinggang Shen

Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice).

Continuous Motion Planning with Temporal Logic Specifications using Deep Neural Networks

no code implementations2 Apr 2020 Chuanzheng Wang, Yi-Nan Li, Stephen L. Smith, Jun Liu

A na\"ive way of solving a motion planning problem with LTL specifications using reinforcement learning is to sample a trajectory and then assign a high reward for training if the trajectory satisfies the entire LTL formula.

Motion Planning Temporal Logic

Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images

no code implementations26 Mar 2020 Zhenyu Tang, Wei Zhao, Xingzhi Xie, Zheng Zhong, Feng Shi, Jun Liu, Dinggang Shen

Purpose: Using machine learning method to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images, and to explore the severity-related features from the resulting assessment model.

Computed Tomography (CT)

Towards Cognitive Routing based on Deep Reinforcement Learning

no code implementations19 Mar 2020 Jiawei Wu, Jianxue Li, Yang Xiao, Jun Liu

Routing is one of the key functions for stable operation of network infrastructure.

Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos

no code implementations15 Mar 2020 Jianqin Yin, Yanchun Wu, Huaping Liu, Yonghao Dang, Zhiyi Liu, Jun Liu

Our work features two-fold: 1) An important insight that deep features extracted for action recognition can well model the self-similarity periodicity of the repetitive action is presented.

Action Recognition

ZSTAD: Zero-Shot Temporal Activity Detection

no code implementations CVPR 2020 Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, ZongYuan Ge, Alexander Hauptmann

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos.

Action Detection Activity Detection

Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation

no code implementations20 Feb 2020 Xiaohong Wang, Xudong Jiang, Henghui Ding, Jun Liu

Accurate segmentation of skin lesion from dermoscopic images is a crucial part of computer-aided diagnosis of melanoma.

Lesion Segmentation

Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning

no code implementations20 Feb 2020 Ke Mei, Chuang Zhu, Lei Jiang, Jun Liu, Yuanyuan Qiao

Experimental results on glomeruli segmentation from renal biopsy images indicate that our network is able to improve segmentation performance on target type of stained images and use unlabeled data to achieve similar accuracy to labeled data.

Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation

no code implementations10 Feb 2020 Jun Liu, Xiangyue Wang, Xue-Cheng Tai

The novelty of our method is to interpret the softmax activation function as a dual variable in a variational problem, and thus many spatial priors can be imposed in the dual space.

Semantic Segmentation

Knowledge forest: a novel model to organize knowledge fragments

no code implementations14 Dec 2019 Qinghua Zheng, Jun Liu, Hongwei Zeng, Zhaotong Guo, Bei Wu, Bifan Wei

Facet trees can organize knowledge fragments with facet hyponymy to alleviate information overload.

D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems

no code implementations28 Nov 2019 Taoxing Pan, Jun Liu, Jie Wang

To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost.

Extended Answer and Uncertainty Aware Neural Question Generation

no code implementations19 Nov 2019 Hongwei Zeng, Zhuo Zhi, Jun Liu, Bifan Wei

In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers.

Question Generation

Performance Analysis on Machine Learning-Based Channel Estimation

no code implementations10 Nov 2019 Kai Mei, Jun Liu, Xiaochen Zhang, Nandana Rajatheva, Jibo Wei

In this situation, our analysis results can be applied to assess the performance and support the design of machine learning-based channel estimation.

Efficient Dynamic WFST Decoding for Personalized Language Models

no code implementations23 Oct 2019 Jun Liu, Jiedan Zhu, Vishal Kathuria, Fuchun Peng

A second layer is a private cache that caches the graph that represents the personalized language model, which is only shared by the utterances from a particular user.

Language Modelling Speech Recognition

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

no code implementations16 Oct 2019 Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng

We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.

Text Generation Transfer Learning

TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction

no code implementations15 Oct 2019 Xiaoli Liu, Jianqin Yin, Jin Liu, Pengxiang Ding, Jun Liu, Huaping Liu

And the global temporal co-occurrence features represent the co-occurrence relationship that different subsequences in a complex motion sequence are appeared simultaneously, which can be obtained automatically with our proposed TrajectoryNet by reorganizing the temporal information as the depth dimension of the input tensor.

Human motion prediction motion prediction +1

Interaction Relational Network for Mutual Action Recognition

1 code implementation11 Oct 2019 Mauricio Perez, Jun Liu, Alex C. Kot

Our solution is able to achieve state-of-the-art performance on the traditional interaction recognition datasets SBU and UT, and also on the mutual actions from the large-scale dataset NTU RGB+D.

Action Recognition Human Interaction Recognition +1

PowerSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization

no code implementations25 Sep 2019 Jun Liu, Beitong Zhou, Weigao Sun, Ruijuan Chen, Claire J. Tomlin, Ye Yuan

In this paper, we propose a novel technique for improving the stochastic gradient descent (SGD) method to train deep networks, which we term \emph{PowerSGD}.

Nonlocal Patches based Gaussian Mixture Model for Image Inpainting

no code implementations22 Sep 2019 Wei Wan, Jun Liu

By a maximum a posteriori (MAP) estimation, we formulate a new regularization term according to the log-likelihood function of the mixture model.

Denoising Image Inpainting

Structured Query Construction via Knowledge Graph Embedding

no code implementations6 Sep 2019 Ruijie Wang, Meng Wang, Jun Liu, Michael Cochez, Stefan Decker

At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query.

Knowledge Graph Embedding Knowledge Graphs

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

2 code implementations12 May 2019 Jun Liu, Amir Shahroudy, Mauricio Perez, Gang Wang, Ling-Yu Duan, Alex C. Kot

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.

Action Recognition One-Shot 3D Action Recognition

HLO: Half-kernel Laplacian Operator for Surface Smoothing

1 code implementation12 May 2019 Wei Pan, Xuequan Lu, Yuanhao Gong, Wenming Tang, Jun Liu, Ying He, Guoping Qiu

This paper presents a simple yet effective method for feature-preserving surface smoothing.

Computational Geometry Graphics

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

4 code implementations14 Apr 2019 Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, Peng Jiang

To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context.

Recommendation Systems

Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image

1 code implementation13 Feb 2019 Siyan Tao, Yao Guo, Chuang Zhu, Huang Chen, Yue Zhang, Jie Yang, Jun Liu

In this paper, we propose a novel method for highly efficient follicular segmentation of thyroid cytopathological WSIs.

General Classification

Skeleton-Based Online Action Prediction Using Scale Selection Network

no code implementations8 Feb 2019 Jun Liu, Amir Shahroudy, Gang Wang, Ling-Yu Duan, Alex C. Kot

Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step.

Skeleton Based Action Recognition

Feature Boosting Network For 3D Pose Estimation

no code implementations15 Jan 2019 Jun Liu, Henghui Ding, Amir Shahroudy, Ling-Yu Duan, Xudong Jiang, Gang Wang, Alex C. Kot

Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation.

3D Hand Pose Estimation 3D Pose Estimation

Deep Neural Network Aided Scenario Identification in Wireless Multi-path Fading Channels

no code implementations23 Nov 2018 Jun Liu, Kai Mei, Dongtang Ma, Jibo Wei

This letter illustrates our preliminary works in deep nerual network (DNN) for wireless communication scenario identification in wireless multi-path fading channels.

Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners

no code implementations ACL 2018 Jun Liu, Hiroyuki Shindo, Yuji Matsumoto

We present a computer-assisted learning system, Jastudy, which is particularly designed for Chinese-speaking learners of Japanese as a second language (JSL) to learn Japanese functional expressions with suggestion of appropriate example sentences.

A Variational Image Segmentation Model based on Normalized Cut with Adaptive Similarity and Spatial Regularization

no code implementations6 Jun 2018 Faqiang Wang, Cuicui Zhao, Jun Liu, Hai-yang Huang

Thus, the segmentation results of the existing Ncut method are largely dependent on a pre-constructed similarity measure on the graph since this measure is usually given empirically by users.

Graph Clustering Semantic Segmentation +1

SSNet: Scale Selection Network for Online 3D Action Prediction

no code implementations CVPR 2018 Jun Liu, Amir Shahroudy, Gang Wang, Ling-Yu Duan, Alex C. Kot

As there are significant temporal scale variations of the observed part of the ongoing action at different progress levels, we propose a novel window scale selection scheme to make our network focus on the performed part of the ongoing action and try to suppress the noise from the previous actions at each time step.

Action Recognition

Deep Convolutional Neural Networks for Map-Type Classification

no code implementations26 May 2018 Xiran Zhou, Wenwen Li, Samantha T. Arundel, Jun Liu

To facilitate establishing an automatic approach for accessing the needed map, this paper reports our investigation into using deep learning techniques to recognize seven types of map, including topographic map, terrain map, physical map, urban scene map, the National Map, 3D map, nighttime map, orthophoto map, and land cover classification map.

Classification General Classification

Convexity Shape Prior for Level Set based Image Segmentation Method

no code implementations22 May 2018 Shi Yan, Xue-Cheng Tai, Jun Liu, Hai-yang Huang

We apply our method to region and edge based level set segmentation models including Chan-Vese (CV) model with guarantee that the segmented region will be convex.

Semantic Segmentation

Variational based Mixed Noise Removal with CNN Deep Learning Regularization

no code implementations21 May 2018 Faqiang Wang, Hai-yang Huang, Jun Liu

In this paper, the traditional model based variational method and learning based algorithms are naturally integrated to address mixed noise removal problem.

Image Reconstruction

Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection

no code implementations3 Nov 2017 Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao, Yirui Wu

In this paper, we propose a new Multi-Glimpse LSTM (MG-LSTM) network, in which multi-scale contextual information is sequentially integrated to promote the human detection performance.

Human Detection

PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking

no code implementations17 Jul 2017 Meng Wang, Jiaheng Zhang, Jun Liu, Wei Hu, Sen Wang, Xue Li, Wenqiang Liu

Electronic medical records contain multi-format electronic medical data that consist of an abundance of medical knowledge.

Entity Linking Knowledge Graphs

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

no code implementations CVPR 2017 Jun Liu, Gang Wang, Ping Hu, Ling-Yu Duan, Alex C. Kot

Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information.

Action Analysis One-Shot 3D Action Recognition +1

Deep Level Sets for Salient Object Detection

no code implementations CVPR 2017 Ping Hu, Bing Shuai, Jun Liu, Gang Wang

Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.

RGB Salient Object Detection Saliency Detection +1

A Procedural Texture Generation Framework Based on Semantic Descriptions

no code implementations13 Apr 2017 Junyu Dong, Li-Na Wang, Jun Liu, Xin Sun

Finally, given a set of semantic descriptions, the diverse properties of the samples in the semantic space can lead the framework to find an appropriate generation model that uses appropriate parameters to produce a desired texture.

Multi-Label Learning Texture Synthesis

Perception Driven Texture Generation

no code implementations24 Mar 2017 Yanhai Gan, Huifang Chi, Ying Gao, Jun Liu, Guoqiang Zhong, Junyu Dong

In this paper, we propose a joint deep network model that combines adversarial training and perceptual feature regression for texture generation, while only random noise and user-defined perceptual attributes are required as input.

Texture Synthesis

Simplification of Example Sentences for Learners of Japanese Functional Expressions

no code implementations WS 2016 Jun Liu, Yuji Matsumoto

Learning functional expressions is one of the difficulties for language learners, since functional expressions tend to have multiple meanings and complicated usages in various situations.

Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

no code implementations24 Jul 2016 Jun Liu, Amir Shahroudy, Dong Xu, Gang Wang

To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell.

Action Analysis Skeleton Based Action Recognition

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

1 code implementation CVPR 2016 Amir Shahroudy, Jun Liu, Tian-Tsong Ng, Gang Wang

Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes.

General Classification Skeleton Based Action Recognition

On the Powerball Method for Optimization

no code implementations24 Mar 2016 Ye Yuan, Mu Li, Jun Liu, Claire J. Tomlin

We propose a new method to accelerate the convergence of optimization algorithms.

Successive Ray Refinement and Its Application to Coordinate Descent for LASSO

no code implementations17 Dec 2015 Jun Liu, Zheng Zhao, Ruiwen Zhang

Coordinate descent is one of the most popular approaches for solving Lasso and its extensions due to its simplicity and efficiency.

A PCA-Based Convolutional Network

no code implementations14 May 2015 Yanhai Gan, Jun Liu, Junyu Dong, Guoqiang Zhong

Particularly, each feature extraction stage includes two layers: a convolutional layer and a feature pooling layer.

Face Recognition Texture Classification

New explicit thresholding/shrinkage formulas for one class of regularization problems with overlapping group sparsity and their applications

no code implementations24 Dec 2013 Gang Liu, Ting-Zhu Huang, Xiao-Guang Lv, Jun Liu

To solve this kind of ill-posed problems, a regularization term (i. e., regularizer) should be introduced, under the assumption that the solutions have some specific properties, such as sparsity and group sparsity.

Compressive Sensing Deblurring +2

Total variation with overlapping group sparsity for image deblurring under impulse noise

no code implementations21 Dec 2013 Gang Liu, Ting-Zhu Huang, Jun Liu, Xiao-Guang Lv

The total variation (TV) regularization method is an effective method for image deblurring in preserving edges.

Deblurring Image Deblurring

Safe and Efficient Screening For Sparse Support Vector Machine

no code implementations30 Oct 2013 Zheng Zhao, Jun Liu

Screening is an effective technique for speeding up the training process of a sparse learning model by removing the features that are guaranteed to be inactive the process.

Sparse Learning

Image Restoration using Total Variation with Overlapping Group Sparsity

no code implementations13 Oct 2013 Jun Liu, Ting-Zhu Huang, Ivan W. Selesnick, Xiao-Guang Lv, Po-Yu Chen

Usually, the high-order total variation (HTV) regularizer is an good option except its over-smoothing property.

Image Restoration

Safe Screening With Variational Inequalities and Its Application to LASSO

no code implementations29 Jul 2013 Jun Liu, Zheng Zhao, Jie Wang, Jieping Ye

Safe screening is gaining increasing attention since 1) solving sparse learning formulations usually has a high computational cost especially when the number of features is large and 2) one needs to try several regularization parameters to select a suitable model.

Feature Selection Sparse Learning

Efficient Mixed-Norm Regularization: Algorithms and Safe Screening Methods

no code implementations16 Jul 2013 Jie Wang, Jun Liu, Jieping Ye

One key building block of the proposed algorithm is the l1q-regularized Euclidean projection (EP_1q).

Sparse Learning

A Safe Screening Rule for Sparse Logistic Regression

no code implementations NeurIPS 2014 Jie Wang, Jiayu Zhou, Jun Liu, Peter Wonka, Jieping Ye

The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection.

Feature Selection

Efficient Methods for Overlapping Group Lasso

no code implementations NeurIPS 2011 Lei Yuan, Jun Liu, Jieping Ye

There have been several recent attempts to study a more general formulation, where groups of features are given, potentially with overlaps between the groups.

Feature Selection

Projection onto A Nonnegative Max-Heap

no code implementations NeurIPS 2011 Jun Liu, Liang Sun, Jieping Ye

In this paper, we show that such Euclidean projection problem admits an analytical solution and we develop a top-down algorithm where the key operation is to find the so-called \emph{maximal root-tree} of the subtree rooted at each node.

Moreau-Yosida Regularization for Grouped Tree Structure Learning

no code implementations NeurIPS 2010 Jun Liu, Jieping Ye

The structured regularization with a pre-defined tree structure is based on a group-Lasso penalty, where one group is defined for each node in the tree.

Learning Brain Connectivity of Alzheimer's Disease from Neuroimaging Data

no code implementations NeurIPS 2009 Shuai Huang, Jing Li, Liang Sun, Jun Liu, Teresa Wu, Kewei Chen, Adam Fleisher, Eric Reiman, Jieping Ye

Recent advances in neuroimaging techniques provide great potentials for effective diagnosis of Alzheimer’s disease (AD), the most common form of dementia.

Efficient Recovery of Jointly Sparse Vectors

no code implementations NeurIPS 2009 Liang Sun, Jun Liu, Jianhui Chen, Jieping Ye

MMV is an extension of the single measurement vector (SMV) model employed in standard compressive sensing (CS).

Compressive Sensing

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