Search Results for author: Jun Liu

Found 183 papers, 38 papers with code

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

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

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 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

SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning

no code implementations15 Mar 2023 Jinxiang Lai, Siqian Yang, Wenlong Wu, Tao Wu, Guannan Jiang, Xi Wang, Jun Liu, Bin-Bin Gao, Wei zhang, Yuan Xie, Chengjie Wang

Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.

Few-Shot Learning

Precise Facial Landmark Detection by Reference Heatmap Transformer

no code implementations14 Mar 2023 Jun Wan, Jun Liu, Jie zhou, Zhihui Lai, Linlin Shen, Hang Sun, Ping Xiong, Wenwen Min

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results.

Facial Landmark Detection

Robustly Complete Finite-State Abstractions for Control Synthesis of Stochastic Systems

no code implementations8 Mar 2023 Yiming Meng, Jun Liu

The essential step of abstraction-based control synthesis for nonlinear systems to satisfy a given specification is to obtain a finite-state abstraction of the original systems.

Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption

no code implementations15 Feb 2023 Jun Liu, Ye Yuan

We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle manifold.

Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

no code implementations1 Feb 2023 Amartya Mukherjee, Jun Liu

The Proximal Policy Optimization (PPO)-Clipped algorithm is improvised with this implementation as it uses a value network to compute the objective function for its policy network.

reinforcement-learning Reinforcement Learning (RL)

Modeling Uncertain Feature Representation for Domain Generalization

1 code implementation16 Jan 2023 Xiaotong Li, Zixuan Hu, Jun Liu, Yixiao Ge, Yongxing Dai, Ling-Yu Duan

In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.

Domain Generalization Image Classification +3

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition

no code implementations8 Jan 2023 Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i. e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective.

Action Recognition Facial Expression Recognition (FER) +2

HDNet: A Hierarchically Decoupled Network for Crowd Counting

no code implementations12 Dec 2022 Chenliang Gu, Changan Wang, Bin-Bin Gao, Jun Liu, Tianliang Zhang

Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution.

Crowd Counting Density Estimation +1

DiffPose: Toward More Reliable 3D Pose Estimation

no code implementations30 Nov 2022 Jia Gong, Lin Geng Foo, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu

Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy.

3D Pose Estimation Monocular 3D Human Pose Estimation

Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision

no code implementations23 Nov 2022 Jiawei Zhan, Jun Liu, Wei Tang, Guannan Jiang, Xi Wang, Bin-Bin Gao, Tianliang Zhang, Wenlong Wu, Wei zhang, Chengjie Wang, Yuan Xie

This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.

Multi-Label Image Classification

tSF: Transformer-based Semantic Filter for Few-Shot Learning

no code implementations2 Nov 2022 Jinxiang Lai, Siqian Yang, Wenlong Liu, Yi Zeng, Zhongyi Huang, Wenlong Wu, Jun Liu, Bin-Bin Gao, Chengjie Wang

Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples.

Few-Shot Learning object-detection +1

Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective

no code implementations2 Nov 2022 Jinxiang Lai, Siqian Yang, Guannan Jiang, Xi Wang, Yuxi Li, Zihui Jia, Xiaochen Chen, Jun Liu, Bin-Bin Gao, Wei zhang, Yuan Xie, Chengjie Wang

In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.

Few-Shot Learning

Improving the Reliability for Confidence Estimation

no code implementations13 Oct 2022 Haoxuan Qu, Yanchao Li, Lin Geng Foo, Jason Kuen, Jiuxiang Gu, Jun Liu

Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.

Image Classification Meta-Learning +1

Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior

no code implementations9 Oct 2022 Xiaole Tang, XiLe Zhao, Jun Liu, Jianli Wang, Yuchun Miao, Tieyong Zeng

To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios.

Deblurring Image Deblurring

Heatmap Distribution Matching for Human Pose Estimation

no code implementations3 Oct 2022 Haoxuan Qu, Li Xu, Yujun Cai, Lin Geng Foo, Jun Liu

In this paper, we show that optimizing the heatmap prediction in such a way, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction.

2D Human Pose Estimation Pose Estimation

Downlink Compression Improves TopK Sparsification

no code implementations30 Sep 2022 William Zou, Hans De Sterck, Jun Liu

One of the largest bottlenecks in distributed training is communicating gradients across different nodes.

Multiple Control Barrier Functions: An Application to Reactive Obstacle Avoidance for a Multi-steering Tractor-trailer System

no code implementations12 Sep 2022 Mohammad Aali, Jun Liu

We develop a control structure based on a multiple CBFs scheme for a multi-steering tractor-trailer system to ensure a collision-free maneuver for both the tractor and trailer in the presence of several obstacles.

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

no code implementations8 Sep 2022 Jinxiang Lai, Wenlong Liu, Jun Liu

Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills.

Continual Learning object-detection +1

Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition

no code implementations3 Sep 2022 Tianjiao Li, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Anran Wang, Jinghua Wang, Jun Liu

We design a novel Dynamic Spatio-Temporal Specialization (DSTS) module, which consists of specialized neurons that are only activated for a subset of samples that are highly similar.

Fine-grained Action Recognition

Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation

no code implementations26 Jul 2022 Guangchen Shi, Yirui Wu, Jun Liu, Shaohua Wan, Wenhai Wang, Tong Lu

Second, to resist overfitting issues caused by few training samples, a hyper-class embedding is learned by clustering all category embeddings for initialization and aligned with category embedding of the new class for enhancement, where learned knowledge assists to learn new knowledge, thus alleviating performance dependence on training data scale.

Few-Shot Semantic Segmentation Semantic Segmentation

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

no code implementations23 Jul 2022 Li Xu, Haoxuan Qu, Jason Kuen, Jiuxiang Gu, Jun Liu

Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video.

Graph Generation Meta-Learning +1

ERA: Expert Retrieval and Assembly for Early Action Prediction

no code implementations20 Jul 2022 Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Qiuhong Ke, Jun Liu

Early action prediction aims to successfully predict the class label of an action before it is completely performed.

Early Action Prediction Retrieval

Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation

1 code implementation21 Jun 2022 Dong Liang, Jun Liu, Kuanquan Wang, Gongning Luo, Wei Wang, Shuo Li

The morphological changes in knee cartilage (especially femoral and tibial cartilages) are closely related to the progression of knee osteoarthritis, which is expressed by magnetic resonance (MR) images and assessed on the cartilage segmentation results.

Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees

1 code implementation4 Jun 2022 Ruikun Zhou, Thanin Quartz, Hans De Sterck, Jun Liu

This paper proposes a learning framework to simultaneously stabilize an unknown nonlinear system with a neural controller and learn a neural Lyapunov function to certify a region of attraction (ROA) for the closed-loop system.

Data-Driven Learning of Safety-Critical Control with Stochastic Control Barrier Functions

no code implementations22 May 2022 Chuanzheng Wang, Yiming Meng, Stephen L. Smith, Jun Liu

More specifically, we propose a data-driven stochastic control barrier function (DDSCBF) framework and use supervised learning to learn the unknown stochastic dynamics via the DDSCBF scheme.

Surface Representation for Point Clouds

1 code implementation CVPR 2022 Haoxi Ran, Jun Liu, Chengjie Wang

Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency.

3D Object Detection 3D Point Cloud Classification +2

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

2 code implementations11 May 2022 Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang

The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.

Image Super-Resolution

Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention

2 code implementations9 May 2022 Wei Dai, Rui Liu, Tianyi Wu, Min Wang, Jianqin Yin, Jun Liu

Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment.

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

1 code implementation2 May 2022 Fangzhi Xu, Jun Liu, Qika Lin, Yudai Pan, Lingling Zhang

Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively.

Logical Reasoning Machine Reading Comprehension

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

1 code implementation CVPR 2022 Xun Long Ng, Kian Eng Ong, Qichen Zheng, Yun Ni, Si Yong Yeo, Jun Liu

More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes.

Animal Action Recognition Animal Pose Estimation +1

Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking

no code implementations18 Mar 2022 Jun Liu, Tong Ruan, Haofen Wang, Huanhuan Zhang

The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging.

Dialogue State Tracking

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

no code implementations8 Mar 2022 Zhiyu Mou, Jun Liu, Xiang Yun, Feifei Gao, Qihui Wu

We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time.

Graph Attention Head Detection +2

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

1 code implementation3 Mar 2022 Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Yi Yang, Ling-Yu Duan

Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.

Domain Generalization Person Re-Identification +1

Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds

no code implementations28 Feb 2022 Shengjing Tian, Jun Liu, Xiuping Liu

In this work, we investigate a more challenging task in the LiDAR point clouds, class-agnostic tracking, where a general model is supposed to be learned for any specified targets of both observed and unseen categories.

Benchmarking Object Tracking

Theoretical Analysis of Deep Neural Networks in Physical Layer Communication

no code implementations21 Feb 2022 Jun Liu, Haitao Zhao, Dongtang Ma, Kai Mei, Jibo Wei

In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity.

Intelligent Communication

On Almost Sure Convergence Rates of Stochastic Gradient Methods

no code implementations9 Feb 2022 Jun Liu, Ye Yuan

We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.

Uncertainty Modeling for Out-of-Distribution Generalization

1 code implementation ICLR 2022 Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, Ling-Yu Duan

In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.

Image Classification Out-of-Distribution Generalization +2

Robust Image Forgery Detection Over Online Social Network Shared Images

1 code implementation CVPR 2022 Haiwei Wu, Jiantao Zhou, Jinyu Tian, Jun Liu

To fight against the OSN-shared forgeries, in this work, a novel robust training scheme is proposed.

Meta Agent Teaming Active Learning for Pose Estimation

no code implementations CVPR 2022 Jia Gong, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu

The existing pose estimation approaches often require a large number of annotated images to attain good estimation performance, which are laborious to acquire.

Active Learning Pose Estimation

En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning

no code implementations CVPR 2022 Xia Kong, Zuodong Gao, Xiaofan Li, Ming Hong, Jun Liu, Chengjie Wang, Yuan Xie, Yanyun Qu

Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space.

Generalized Zero-Shot Learning

Under-Approximate Reachability Analysis for a Class of Linear Systems with Inputs

no code implementations27 Dec 2021 Mohamed Serry, Jun Liu

Under-approximations of reachable sets and tubes have been receiving growing research attention due to their important roles in control synthesis and verification.

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve

no code implementations23 Dec 2021 Lei Wang, Jun Liu, Piotr Koniusz

In this paper, we propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE).

Dynamic Time Warping Few-Shot action recognition +3

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

1 code implementation4 Dec 2021 Feng Xu, Chuang Zhu, Wenqi Tang, Ying Wang, Yu Zhang, Jie Li, Hongchuan Jiang, Zhongyue Shi, Jun Liu, Mulan Jin

Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.

Multiple Instance Learning Specificity +1

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 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 Privacy Preserving

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.

BIG-bench Machine Learning

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 +2

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.

Clinical Knowledge Lesion Segmentation +2

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

no code implementations2 Jun 2021 Jun Liu, Haitao Zhao, Dongtang Ma, Kai Mei, 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

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

2 code implementations 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

2 code implementations 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 Benchmarking +4

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.

Radar waveform design

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

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

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

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

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

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 +1

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 Automatic Speech Recognition (ASR) +2

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.

Depth Prediction Indoor Localization +2

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 regression +1

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.

Smooth Converse Lyapunov-Barrier Theorems for Asymptotic Stability with Safety Constraints and Reach-Avoid-Stay Specifications

no code implementations9 Sep 2020 Yiming Meng, Yinan Li, Maxwell Fitzsimmons, Jun Liu

While the converse Lyapunov-barrier theorems are not constructive, as with classical converse Lyapunov theorems, we believe that the unified necessary and sufficient conditions with a single Lyapunov-barrier function are of theoretical interest and can hopefully shed some light on computational approaches.

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.

reinforcement-learning Reinforcement Learning (RL)

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.

BIG-bench Machine Learning

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

2 code implementations29 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.

Tumor Segmentation

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.

Depth Prediction Monocular Depth Estimation +1

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 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

1 code implementation25 May 2020 Xiaoli Liu, Jianqin Yin, Huaping Liu, Jun Liu

In contrast to prior works, we improve the multi-order modeling ability of human motion systems for more accurate predictions by building a deep state-space model (DeepSSM).

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

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 reinforcement-learning +1

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)

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 Skin Lesion Segmentation

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

1 code implementation20 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.

Image Segmentation 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 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.

BIG-bench Machine Learning

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 +1

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.

Response Generation Text Generation +1

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

3 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 +1

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

7 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.

Sequential Recommendation

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 Image Segmentation +2

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 Temporal Action Localization

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.

Image Segmentation 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

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.

object-detection RGB Salient Object Detection +2

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

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.