Search Results for author: Jie Li

Found 117 papers, 34 papers with code

Geometry-Based Stochastic Line-of-Sight Probability Model for A2G Channels under Urban Scenarios

no code implementations6 Sep 2021 Qiuming Zhu, Fei Bai, Minghui Pang, Jie Li, Weizhi Zhong, Xiaomin Chen, Kai Mao

Line-of-sight (LoS) path is essential for the reliability of air-to-ground (A2G) communications, but the existence of LoS path is difficult to predict due to random obstacles on the ground.

Stimuli-Aware Visual Emotion Analysis

no code implementations4 Sep 2021 Jingyuan Yang, Jie Li, Xiumei Wang, Yuxuan Ding, Xinbo Gao

Then, we design three specific networks, i. e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously.

Emotion Recognition

An Integrated Framework for the Heterogeneous Spatio-Spectral-Temporal Fusion of Remote Sensing Images

no code implementations1 Sep 2021 Menghui Jiang, Huanfeng Shen, Jie Li, Liangpei Zhang

Images from many remote sensing satellites, including MODIS, Landsat-8, Sentinel-1, and Sentinel-2, are utilized in the experiments.

LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision

no code implementations26 Aug 2021 Zhijian Liu, Simon Stent, Jie Li, John Gideon, Song Han

Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets.

Image Classification Instance Segmentation +2

Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion

no code implementations13 Aug 2021 Huanfeng Shen, Menghui Jiang, Jie Li, Chenxia Zhou, Qiangqiang Yuan, Liangpei Zhang

In this paper, we systematically investigate the coupling of model-driven and data-driven methods, which has rarely been considered in the remote sensing image restoration and fusion communities.

Image Restoration

Is Pseudo-Lidar needed for Monocular 3D Object detection?

1 code implementation13 Aug 2021 Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, Adrien Gaidon

Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors.

 Ranked #1 on Monocular 3D Object Detection on KITTI Cars Moderate (using extra training data)

Monocular 3D Object Detection Monocular Depth Estimation +1

A Dynamic 3D Spontaneous Micro-expression Database: Establishment and Evaluation

no code implementations31 Jul 2021 Fengping Wang, Jie Li, Chun Qi, Yun Zhang, Danmin Miao

Micro-expressions are spontaneous, unconscious facial movements that show people's true inner emotions and have great potential in related fields of psychological testing.


Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle

no code implementations27 Jul 2021 Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu

UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.

Keypoint Detection

Wideband photonic blind source separation with optical pulse sampling

no code implementations21 Jul 2021 Taichu Shi, Yang Qi, Weipeng Zhang, Paul R. Prucnal, Jie Li, Ben Wu

The ultra-fast optical pulse functions as a tweezer that collects samples of the signals at very low sampling rates, and each sample is short enough to maintain the statistical properties of the signals.

Rethinking the Tradeoff in Integrated Sensing and Communication: Recognition Accuracy versus Communication Rate

no code implementations20 Jul 2021 Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Fan Liu, Meihong Zhang, Xiaohui Peng, Tony Xiao Han

Integrated sensing and communication (ISAC) is a promising technology to improve the band-utilization efficiency via spectrum sharing or hardware sharing between radar and communication systems.

Fully Polarimetric SAR and Single-Polarization SAR Image Fusion Network

no code implementations18 Jul 2021 Liupeng Lin, Jie Li, Huanfeng Shen, Lingli Zhao, Qiangqiang Yuan, Xinghua Li

The data fusion technology aims to aggregate the characteristics of different data and obtain products with multiple data advantages.

IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement

no code implementations29 Jun 2021 Jie Li, Laiyan Ding, Rui Huang

3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features.

2D Semantic Segmentation indoor scene understanding +1

A Circular-Structured Representation for Visual Emotion Distribution Learning

no code implementations CVPR 2021 Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, Xinbo Gao

Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks.

Emotion Recognition

GPLA-12: An Acoustic Signal Dataset of Gas Pipeline Leakage

2 code implementations19 Jun 2021 Jie Li, Lizhong Yao

In this paper, we introduce a new acoustic leakage dataset of gas pipelines, called as GPLA-12, which has 12 categories over 684 training/testing acoustic signals.

Fault Detection Time Series

Learning the Non-Differentiable Optimization for Blind Super-Resolution

no code implementations CVPR 2021 Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao

Instead of considering iterative strategy, we make the blur kernel predictor trainable in the whole blind SR model, in which AMNet is well-trained.


Inverse Simulation: Reconstructing Dynamic Geometry of Clothed Humans via Optimal Control

no code implementations CVPR 2021 Jingfan Guo, Jie Li, Rahul Narain, Hyun Soo Park

Inspired by the theory of optimal control, we optimize the body states such that the simulated cloth motion is matched to the point cloud measurements, and the analytic gradient of the simulator is back-propagated to update the body states.

Hierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation

no code implementations CVPR 2021 Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon

We use a hierarchical Lovasz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.

Instance Segmentation Panoptic Segmentation

Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation

no code implementations8 Jun 2021 Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon

We use a hierarchical Lov\'asz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.

Instance Segmentation Panoptic Segmentation

Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack

no code implementations3 May 2021 Yixu Wang, Jie Li, Hong Liu, Yan Wang, Yongjian Wu, Feiyue Huang, Rongrong Ji

We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.

Knowledge Distillation

Exploring Multi-dimensional Data via Subset Embedding

no code implementations24 Apr 2021 Peng Xie, Wenyuan Tao, Jie Li, Wentao Huang, Siming Chen

The core of the approach is a subset embedding network (SEN) that represents a group of subsets as uniformly-formatted embeddings.

Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model

no code implementations21 Apr 2021 Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Xiaohui Peng, Tony Xiao Han

Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing.

Scene Understanding

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

2 code implementations CVPR 2021 Tianwei Lin, Zhuoqi Ma, Fu Li, Dongliang He, Xin Li, Errui Ding, Nannan Wang, Jie Li, Xinbo Gao

Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).

Style Transfer

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

no code implementations30 Mar 2021 Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation.

Monocular Depth Estimation Semantic Segmentation +1

Transitive Learning: Exploring the Transitivity of Degradations for Blind Super-Resolution

1 code implementation29 Mar 2021 Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Wen Lu

We then propose a novel Transitive Learning method for blind Super-Resolution on transitive degradations (TLSR), by adaptively inferring a transitive transformation function to solve the unknown degradations without any iterative operations in inference.


Learning to Track with Object Permanence

1 code implementation26 Mar 2021 Pavel Tokmakov, Jie Li, Wolfram Burgard, Adrien Gaidon

In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning.

Multi-Object Tracking Object Detection +1

Approximate Optimal Filter for Linear Gaussian Time-invariant Systems

no code implementations9 Mar 2021 Kaiming Tang, Shengbo Eben Li, Yuming Yin, Yang Guan, Jingliang Duan, Wenhan Cao, Jie Li

The equivalence holds given certain conditions about initial state distributions and policy formats, in which the system state is the estimation error, control input is the filter gain, and control objective function is the accumulated estimation error.

Mixed Policy Gradient

1 code implementation23 Feb 2021 Yang Guan, Jingliang Duan, Shengbo Eben Li, Jie Li, Jianyu Chen, Bo Cheng

MPG contains two types of PG: 1) data-driven PG, which is obtained by directly calculating the derivative of the learned Q-value function with respect to actions, and 2) model-driven PG, which is calculated using BPTT based on the model-predictive return.

Decision Making

DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds

no code implementations7 Feb 2021 Jie Li, Yu Hu

In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer.

3D Object Detection

Long time-series NDVI reconstruction in cloud-prone regions via spatio-temporal tensor completion

no code implementations4 Feb 2021 Dong Chu, Huanfeng Shen, Xiaobin Guan, Jing M. Chen, Xinghua Li, Jie Li, Liangpei Zhang

The applications of Normalized Difference Vegetation Index (NDVI) time-series data are inevitably hampered by cloud-induced gaps and noise.

Time Series

Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction

no code implementations28 Jan 2021 Jinjiang Guo, Jie Li, Dawei Leng, Lurong Pan

Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data.

Link Prediction

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

no code implementations26 Dec 2020 Hsu-kuang Chiu, Jie Li, Rares Ambrus, Jeannette Bohg

Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association.

Autonomous Driving Multi-Object Tracking +1

Two-Dimensional Multifunctional Materials from Endohedral Fullerenes

no code implementations23 Dec 2020 Jie Li, Ruqian Wu

A new multifunctional 2D material is theoretically predicted based on systematic ab-initio calculations and model simulations for the honeycomb lattice of endohedral fullerene W@C28 molecules.

Materials Science Computational Physics

Skeleton-based Approaches based on Machine Vision: A Survey

no code implementations23 Dec 2020 Jie Li, Binglin Li, Min Gao

Recently, skeleton-based approaches have achieved rapid progress on the basis of great success in skeleton representation.

Object Detection

Coherent mechanical noise cancellation and cooperativity competition in optomechanical arrays

no code implementations21 Dec 2020 Matthijs H. J. de Jong, Jie Li, Claus Gärtner, Richard A. Norte, Simon Gröblacher

We study a multi-resonator optomechanical system, consisting of two SiN membranes coupled to a single optical cavity mode.

Optics Mesoscale and Nanoscale Physics

6 GHz hyperfast rotation of an optically levitated nanoparticle in vacuum

no code implementations17 Dec 2020 Yuanbin Jin, Jiangwei Yan, Shah Jee Rahman, Jie Li, Xudong Yu, Jing Zhang

We measure a highest rotation frequency about 4. 3 GHz of the trapped nanoparticle without feedback cooling and a 6 GHz rotation with feedback cooling, which is the fastest mechanical rotation ever reported to date.

Optics Mesoscale and Nanoscale Physics Quantum Physics

Anatomy of Multipath BGP Deployment in a Large ISP Network

1 code implementation14 Dec 2020 Jie Li, Vasileios Giotsas, Shi Zhou

Our work provides insights into the latest deployment of M-BGP in a major ISP network and it highlights the characteristics and effectiveness of M-BGP as a means to realize load sharing.

Networking and Internet Architecture

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

1 code implementation7 Dec 2020 Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.

Autonomous Driving Point Cloud Segmentation +1

Generative and Discriminative Learning for Distorted Image Restoration

no code implementations11 Nov 2020 Yi Gu, Yuting Gao, Jie Li, Chentao Wu, Weijia Jia

Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task.

Image Restoration Rectification

The Occurrence of Rocky Habitable Zone Planets Around Solar-Like Stars from Kepler Data

1 code implementation28 Oct 2020 Steve Bryson, Michelle Kunimoto, Ravi K. Kopparapu, Jeffrey L. Coughlin, William J. Borucki, David Koch, Victor Silva Aguirre, Christopher Allen, Geert Barentsen, Natalie. M. Batalha, Travis Berger, Alan Boss, Lars A. Buchhave, Christopher J. Burke, Douglas A. Caldwell, Jennifer R. Campbell, Joseph Catanzarite, Hema Chandrasekharan, William J. Chaplin, Jessie L. Christiansen, Jorgen Christensen-Dalsgaard, David R. Ciardi, Bruce D. Clarke, William D. Cochran, Jessie L. Dotson, Laurance R. Doyle, Eduardo Seperuelo Duarte, Edward W. Dunham, Andrea K. Dupree, Michael Endl, James L. Fanson, Eric B. Ford, Maura Fujieh, Thomas N. Gautier III, John C. Geary, Ronald L Gilliland, Forrest R. Girouard, Alan Gould, Michael R. Haas, Christopher E. Henze, Matthew J. Holman, Andrew Howard, Steve B. Howell, Daniel Huber, Roger C. Hunter, Jon M. Jenkins, Hans Kjeldsen, Jeffery Kolodziejczak, Kipp Larson, David W. Latham, Jie Li, Savita Mathur, Soren Meibom, Chris Middour, Robert L. Morris, Timothy D. Morton, Fergal Mullally, Susan E. Mullally, David Pletcher, Andrej Prsa, Samuel N. Quinn, Elisa V. Quintana, Darin Ragozzine, Solange V. Ramirez, Dwight T. Sanderfer, Dimitar Sasselov, Shawn E. Seader, Megan Shabram, Avi Shporer, Jeffrey C. Smith, Jason H. Steffen, Martin Still, Guillermo Torres, John Troeltzsch, Joseph D. Twicken, Akm Kamal Uddin, Jeffrey E. Van Cleve, Janice Voss, Lauren Weiss, William F. Welsh, Bill Wohler, Khadeejah A Zamudio

We present occurrence rates for rocky planets in the habitable zones (HZ) of main-sequence dwarf stars based on the Kepler DR25 planet candidate catalog and Gaia-based stellar properties.

Earth and Planetary Astrophysics Solar and Stellar Astrophysics

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution

1 code implementation28 Sep 2020 Yuanfei Huang, Jie Li, Xinbo Gao, Yanting Hu, Wen Lu

To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.

Image Super-Resolution

A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks

no code implementations18 Sep 2020 Ruoxin Chen, Jie Li, Chentao Wu, Bin Sheng, Ping Li

Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set.

Data Poisoning

Extending Label Smoothing Regularization with Self-Knowledge Distillation

no code implementations11 Sep 2020 Ji-Yue Wang, Pei Zhang, Wen-feng Pang, Jie Li

The experiment results confirm that the TC can help LsrKD and MrKD to boost training, especially on the networks they are failed.

Knowledge Distillation

A Density-Aware PointRCNN for 3D Object Detection in Point Clouds

no code implementations11 Sep 2020 Jie Li, Yu Hu

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds.

3D Object Detection

A Light-Weight Object Detection Framework with FPA Module for Optical Remote Sensing Imagery

no code implementations7 Sep 2020 Xi Gu, Lingbin Kong, Zhicheng Wang, Jie Li, Zhaohui Yu, Gang Wei

On the DOTA dataset, CenterFPANet mAP is 64. 00%, and FPS is 22. 2, which is close to the accuracy of the anchor-based methods currently used and much faster than them.

Object Detection

Align Deep Features for Oriented Object Detection

3 code implementations21 Aug 2020 Jiaming Han, Jian Ding, Jie Li, Gui-Song Xia

However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.

Object Detection In Aerial Images

PillarFlow: End-to-end Birds-eye-view Flow Estimation for Autonomous Driving

no code implementations3 Aug 2020 Kuan-Hui Lee, Matthew Kliemann, Adrien Gaidon, Jie Li, Chao Fang, Sudeep Pillai, Wolfram Burgard

In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning.

Autonomous Driving

Giant magnetic anisotropy energy and long coherence time of uranium substitution on defected Al2O3(0001)

no code implementations14 Jul 2020 Jie Li, Lei Gu, Ruqian Wu

Nanomagnets with giant magnetic anisotropy energy and long coherence time are desired for various technological innovations such as quantum information procession and storage.

Materials Science Computational Physics

Ternary Policy Iteration Algorithm for Nonlinear Robust Control

no code implementations14 Jul 2020 Jie Li, Shengbo Eben Li, Yang Guan, Jingliang Duan, Wenyu Li, Yuming Yin

The simulation results show that the TPI algorithm can converge to the optimal solution for the linear plant, and has high resistance to disturbances for the nonlinear plant.

Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data

no code implementations3 Jul 2020 Feifei Huang, Jie Li, Xuelin Zhu

Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods.

Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction

no code implementations25 Jun 2020 Zhenxi Zhang, Chunna Tian, Jie Li, Zhusi Zhong, Zhicheng Jiao, Xinbo Gao

Further, we propose a context encoding module to utilize the global predictor from the error map to enhance the feature representation and regularize the networks.

Medical Image Segmentation

Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

no code implementations25 May 2020 Bing Cao, Nannan Wang, Xinbo Gao, Jie Li, Zhifeng Li

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.

Face Recognition Heterogeneous Face Recognition +1

Projection & Probability-Driven Black-Box Attack

1 code implementation CVPR 2020 Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, Qi Tian

For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

1 code implementation CVPR 2020 Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan

In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

no code implementations28 Feb 2020 Jie Huang, Cheng-Xiang Wang, Lu Bai, Jian Sun, Yang Yang, Jie Li, Olav Tirkkonen, Ming-Tuo Zhou

This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

1 code implementation ICLR 2020 Vitor Guizilini, Rui Hou, Jie Li, Rares Ambrus, Adrien Gaidon

Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.

Monocular Depth Estimation Representation Learning +2

3D Gated Recurrent Fusion for Semantic Scene Completion

no code implementations17 Feb 2020 Yu Liu, Jie Li, Qingsen Yan, Xia Yuan, Chunxia Zhao, Ian Reid, Cesar Cadena

This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.

Scene Understanding

Facial Attribute Capsules for Noise Face Super Resolution

no code implementations16 Feb 2020 Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Xinbo Gao, Zhifeng Li

In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.

Image Super-Resolution

Video Face Super-Resolution with Motion-Adaptive Feedback Cell

no code implementations15 Feb 2020 Jingwei Xin, Nannan Wang, Jie Li, Xinbo Gao, Zhifeng Li

Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.

Motion Compensation Motion Estimation +2

Image Fine-grained Inpainting

2 code implementations7 Feb 2020 Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao

Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.

Facial Inpainting Fine-Grained Image Inpainting

Direct and indirect reinforcement learning

no code implementations23 Dec 2019 Yang Guan, Shengbo Eben Li, Jingliang Duan, Jie Li, Yangang Ren, Qi Sun, Bo Cheng

Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks.

Decision Making

HighEr-Resolution Network for Image Demosaicing and Enhancing

1 code implementation19 Nov 2019 Kangfu Mei, Juncheng Li, Jiajie Zhang, Hao-Yu Wu, Jie Li, Rui Huang

However, plenty of studies have shown that global information is crucial for image restoration tasks like image demosaicing and enhancing.


Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates

1 code implementation22 Oct 2019 Yalong Liu, Jie Li, Miaomiao Wang, Zhicheng Jiao, Jian Yang, Xianjun Li

In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images.

Two Stream Networks for Self-Supervised Ego-Motion Estimation

no code implementations4 Oct 2019 Rares Ambrus, Vitor Guizilini, Jie Li, Sudeep Pillai, Adrien Gaidon

Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues.

Data Augmentation Motion Estimation +1

Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances

no code implementations4 Oct 2019 Vitor Guizilini, Jie Li, Rares Ambrus, Sudeep Pillai, Adrien Gaidon

Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks.

Monocular Depth Estimation

ViLiVO: Virtual LiDAR-Visual Odometry for an Autonomous Vehicle with a Multi-Camera System

no code implementations30 Sep 2019 Zhenzhen Xiang, Jingrui Yu, Jie Li, Jianbo Su

As for the pose tracker, we propose a visual odometry system fusing both the feature matching and the virtual LiDAR scan matching results.

Monocular Visual Odometry Pose Estimation +1

Boosting Real-Time Driving Scene Parsing with Shared Semantics

1 code implementation16 Sep 2019 Zhenzhen Xiang, Anbo Bao, Jie Li, Jianbo Su

On the other hand, feature fusion modules are designed to combine different modal of semantic features, which leverage the information from both inputs for better accuracy.

Autonomous Driving Scene Parsing +1

The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform

1 code implementation19 Aug 2019 Jie Li, Haifeng Liu, Chuanghua Gui, Jianyu Chen, Zhenyun Ni, Ning Wang

We present the design and implementation of a visual search system for real time image retrieval on JD. com, the world's third largest and China's largest e-commerce site.

Image Retrieval

PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection

no code implementations9 Aug 2019 Qiankun Tang, Shice Liu, Jie Li, Yu Hu

We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives.

Object Detection

Progressive Perception-Oriented Network for Single Image Super-Resolution

1 code implementation24 Jul 2019 Zheng Hui, Jie Li, Xinbo Gao, Xiumei Wang

In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network.

Image Super-Resolution

Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning

no code implementations27 Jun 2019 Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao

In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.

Image Reconstruction Knowledge Distillation +1

Refined-Segmentation R-CNN: A Two-stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants

1 code implementation24 Jun 2019 Yalong Liu, Jie Li, Ying Wang, Miaomiao Wang, Xianjun Li, Zhicheng Jiao, Jian Yang, Xingbo Gao

In this paper, we construct an efficient two-stage PWML semantic segmentation network based on the characteristics of the lesion, called refined segmentation R-CNN (RS RCNN).

Lesion Segmentation

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

no code implementations17 Jun 2019 Zhusi Zhong, Jie Li, Zhenxi Zhang, Zhicheng Jiao, Xinbo Gao

We train the deep encoder-decoder for landmark detection, and combine global landmark configuration with local high-resolution feature responses.

Enhancement of Power Equipment Management Using Knowledge Graph

no code implementations28 Apr 2019 Yachen Tang, Tingting Liu, Guangyi Liu, Jie Li, Renchang Dai, Chen Yuan

Because of data duplication, database decentralization, weak data relations, and sluggish data updates, the power asset management system eager to adopt a new strategy to avoid the information losses, bias, and improve the data storage efficiency and extraction process.

No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancement

2 code implementations18 Apr 2019 Jia Yan, Jie Li, Xin Fu

No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image.

No-Reference Image Quality Assessment SSIM

Shared Predictive Cross-Modal Deep Quantization

no code implementations16 Apr 2019 Erkun Yang, Cheng Deng, Chao Li, Wei Liu, Jie Li, DaCheng Tao

In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search.


Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

no code implementations26 Mar 2019 Yayu Peng, Yishen Wang, Xiao Lu, Haifeng Li, Di Shi, Zhiwei Wang, Jie Li

Short-term load forecasting (STLF) is essential for the reliable and economic operation of power systems.

Load Forecasting

RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion

no code implementations CVPR 2019 Jie Li, Yu Liu, Dong Gong, Qinfeng Shi, Xia Yuan, Chunxia Zhao, Ian Reid

RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).

Scene Labeling

Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning

1 code implementation15 Jan 2019 Guanyu Gao, Jie Li, Yonggang Wen

We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants.

Learning to Fuse Things and Stuff

no code implementations4 Dec 2018 Jie Li, Allan Raventos, Arjun Bhargava, Takaaki Tagawa, Adrien Gaidon

We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation.

Ranked #14 on Panoptic Segmentation on Cityscapes val (using extra training data)

Instance Segmentation Panoptic Segmentation

Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context

no code implementations26 Nov 2018 Jie Li, Yahui Shan, Xiaorui Wang, Yan Li

The use of future contextual information is typically shown to be helpful for acoustic modeling.

TESS full orbital phase curve of the WASP-18b system

1 code implementation14 Nov 2018 Avi Shporer, Ian Wong, Chelsea X. Huang, Michael R. Line, Keivan G. Stassun, Tara Fetherolf, Stephen R. Kane, Luke G. Bouma, Tansu Daylan, Maximilian N. Guenther, George R. Ricker, David W. Latham, Roland Vanderspek, Sara Seager, Joshua N. Winn, Jon M. Jenkins, Ana Glidden, Zach Berta-Thompson, Eric B. Ting, Jie Li, Kari Haworth

The phase curve includes the transit, secondary eclipse, and sinusoidal modulations across the orbital phase shaped by the planet's atmospheric characteristics and the star-planet gravitational interaction.

Earth and Planetary Astrophysics Solar and Stellar Astrophysics

Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

no code implementations1 Nov 2018 Hu Han, Jie Li, Anil K. Jain, Shiguang Shan, Xilin Chen

To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning.

Image Retrieval Multi-Task Learning +2

SPIGAN: Privileged Adversarial Learning from Simulation

no code implementations ICLR 2019 Kuan-Hui Lee, German Ros, Jie Li, Adrien Gaidon

Deep Learning for Computer Vision depends mainly on the source of supervision. Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance.

Image-to-Image Translation Semantic Segmentation +1

Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network

1 code implementation1 Oct 2018 Qiang Zhang, Qiangqiang Yuan, Jie Li, Xin-Xin Liu, Huanfeng Shen, Liangpei Zhang

The existence of hybrid noise in hyperspectral images (HSIs) severely degrades the data quality, reduces the interpretation accuracy of HSIs, and restricts the subsequent HSIs applications.


Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution

no code implementations28 Sep 2018 Yanting Hu, Jie Li, Yuanfei Huang, Xinbo Gao

To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a sequence of feature-modulation memory (FMM) modules is cascaded with a densely connected structure to transform low-resolution features to high informative features.

Image Reconstruction Image Super-Resolution

Spatial-Spectral Fusion by Combining Deep Learning and Variation Model

no code implementations4 Sep 2018 Huanfeng Shen, Menghui Jiang, Jie Li, Qiangqiang Yuan, Yanchong Wei, Liangpei Zhang

In the field of spatial-spectral fusion, the model-based method and the deep learning (DL)-based method are state-of-the-art.

Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint

no code implementations26 Jul 2018 Miaopeng Li, Zimeng Zhou, Jie Li, Xinguo Liu

In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods.

Multi-Person Pose Estimation

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

2 code implementations1 Jun 2018 Qiangqiang Yuan, Qiang Zhang, Jie Li, Huanfeng Shen, Liangpei Zhang

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications.

Hyperspectral Image Denoising Image Denoising

Gated Recurrent Unit Based Acoustic Modeling with Future Context

no code implementations18 May 2018 Jie Li, Xiaorui Wang, Yuan-Yuan Zhao, Yan Li

The use of future contextual information is typically shown to be helpful for acoustic modeling.

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization System

no code implementations15 Apr 2018 Qiyue Li, Heng Qu, Zhi Liu, Nana Zhou, Wei Sun, Jie Li

Based on the extended fingerprint database, the accuracy of indoor localization system can be improved with reduced human effort.

Networking and Internet Architecture

Single Image Super-Resolution via Cascaded Multi-Scale Cross Network

no code implementations24 Feb 2018 Yanting Hu, Xinbo Gao, Jie Li, Yuanfei Huang, Hanzi Wang

To improve information flow and to capture sufficient knowledge for reconstructing the high-frequency details, we propose a cascaded multi-scale cross network (CMSC) in which a sequence of subnetworks is cascaded to infer high resolution features in a coarse-to-fine manner.

Image Reconstruction Image Super-Resolution

Restricting Greed in Training of Generative Adversarial Network

no code implementations28 Nov 2017 Haoxuan You, Zhicheng Jiao, Haojun Xu, Jie Li, Ying Wang, Xinbo Gao

Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning.

Learning a Dilated Residual Network for SAR Image Despeckling

1 code implementation9 Sep 2017 Qiang Zhang, Qiangqiang Yuan, Jie Li, Zhen Yang, Xiaoshuang Ma

In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose a novel deep learning approach by learning a non-linear end-to-end mapping between the noisy and clean SAR images with a dilated residual network (SAR-DRN).

Sar Image Despeckling

A survey of dimensionality reduction techniques based on random projection

no code implementations14 Jun 2017 Haozhe Xie, Jie Li, Hanqing Xue

Dimensionality reduction techniques play important roles in the analysis of big data.

Dimensionality Reduction

WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images

1 code implementation23 Feb 2017 Jie Li, Katherine A. Skinner, Ryan M. Eustice, Matthew Johnson-Roberson

Due to the depth-dependent water column effects inherent to underwater environments, we show that our end-to-end network implicitly learns a coarse depth estimate of the underwater scene from monocular underwater images.

Random Sampling for Fast Face Sketch Synthesis

no code implementations8 Jan 2017 Nannan Wang, Xinbo Gao, Jie Li

The most time-consuming or main computation complexity for exemplar-based face sketch synthesis methods lies in the neighbor selection process.

Face Hallucination Face Sketch Synthesis

Sparse Graphical Representation based Discriminant Analysis for Heterogeneous Face Recognition

no code implementations1 Jul 2016 Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li

An adaptive sparse graphical representation scheme is designed to represent heterogeneous face images, where a Markov networks model is constructed to generate adaptive sparse vectors.

Face Recognition Heterogeneous Face Recognition

Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics

no code implementations25 Mar 2016 Nannan Wang, Jie Li, Leiyu Sun, Bin Song, Xinbo Gao

In this paper, we proposed a synthesized face sketch recognition framework based on full-reference image quality assessment metrics.

Face Recognition Face Sketch Synthesis +2

Graphical Representation for Heterogeneous Face Recognition

no code implementations2 Mar 2015 Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li

Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i. e., different sensors or different wavelengths) for identification.

Face Recognition Heterogeneous Face Recognition

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