Search Results for author: Qi. Wang

Found 50 papers, 11 papers with code

A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View

no code implementations29 Sep 2020 Zhiyuan Zhao, Tao Han, Junyu. Gao, Qi. Wang, Xuelong. Li

Drones shooting can be applied in dynamic traffic monitoring, object detecting and tracking, and other vision tasks.

Crowd Counting Density Estimation +2

Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables

no code implementations ICML 2020 Qi. Wang, Herke van Hoof

Neural processes (NPs) constitute a family of variational approximate models for stochastic processes with promising properties in computational efficiency and uncertainty quantification.

Variational Inference

iPhantom: a framework for automated creation of individualized computational phantoms and its application to CT organ dosimetry

no code implementations20 Aug 2020 Wanyi Fu, Shobhit Sharma, Ehsan Abadi, Alexandros-Stavros Iliopoulos, Qi. Wang, Joseph Y. Lo, Xiaobai Sun, William P. Segars, Ehsan Samei

Objective: This study aims to develop and validate a novel framework, iPhantom, for automated creation of patient-specific phantoms or digital-twins (DT) using patient medical images.

Pixel-wise Crowd Understanding via Synthetic Data

no code implementations30 Jul 2020 Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan

To be specific, 1) supervised crowd understanding: pre-train a crowd analysis model on the synthetic data, then fine-tune it using the real data and labels, which makes the model perform better on the real world; 2) crowd understanding via domain adaptation: translate the synthetic data to photo-realistic images, then train the model on translated data and labels.

Crowd Counting Domain Adaptation

Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos

no code implementations13 Jul 2020 Lifang Wu, Zhou Yang, Qi. Wang, Meng Jian, Boxuan Zhao, Junchi Yan, Chang Wen Chen

Based on the observations, we propose a scheme to fuse global and local motion patterns (MPs) and key visual information (KVI) for semantic event recognition in basketball videos.

Group Activity Recognition Optical Flow Estimation

Stable and Efficient Policy Evaluation

no code implementations6 Jun 2020 Daoming Lyu, Bo Liu, Matthieu Geist, Wen Dong, Saad Biaz, Qi. Wang

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy.

reinforcement-learning

Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm

no code implementations2 May 2020 Alexander Dunn, Qi. Wang, Alex Ganose, Daniel Dopp, Anubhav Jain

The reference algorithm, Automatminer, is a highly-extensible, fully-automated ML pipeline for predicting materials properties from materials primitives (such as composition and crystal structure) without user intervention or hyperparameter tuning.

Materials Science Computational Physics

Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting

1 code implementation5 Apr 2020 Qi. Wang, Tao Han, Junyu. Gao, Yuan Yuan

Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters.

Crowd Counting Domain Adaptation +1

CNN-based Density Estimation and Crowd Counting: A Survey

2 code implementations28 Mar 2020 Guangshuai Gao, Junyu. Gao, Qingjie Liu, Qi. Wang, Yunhong Wang

Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields.

Crowd Counting Density Estimation +1

Pixel-Level Self-Paced Learning for Super-Resolution

1 code implementation6 Mar 2020 Wei. Lin, Junyu. Gao, Qi. Wang, Xuelong. Li

Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields.

Super-Resolution

Focus on Semantic Consistency for Cross-domain Crowd Understanding

no code implementations20 Feb 2020 Tao Han, Junyu. Gao, Yuan Yuan, Qi. Wang

According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information.

Domain Adaptation

A critical examination of compound stability predictions from machine-learned formation energies

3 code implementations28 Jan 2020 Christopher J. Bartel, Amalie Trewartha, Qi. Wang, Alex Dunn, Anubhav Jain, Gerbrand Ceder

By testing seven machine learning models for formation energy on stability predictions using the Materials Project database of DFT calculations for 85, 014 unique chemical compositions, we show that while formation energies can indeed be predicted well, all compositional models perform poorly on predicting the stability of compounds, making them considerably less useful than DFT for the discovery and design of new solids.

Materials Science Computational Physics

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization

4 code implementations10 Jan 2020 Qi. Wang, Junyu. Gao, Wei. Lin, Xuelong. Li

In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc.

Crowd Counting

Detecting AI Trojans Using Meta Neural Analysis

1 code implementation8 Oct 2019 Xiaojun Xu, Qi. Wang, Huichen Li, Nikita Borisov, Carl A. Gunter, Bo Li

To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution.

Data Poisoning

PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain

1 code implementation24 Sep 2019 Dongling Xiao, Chang Liu, Qi. Wang, Chao Wang, Xin Zhang

For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required.

Classification General Classification +1

SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting

no code implementations10 Aug 2019 Junyu. Gao, Qi. Wang, Yuan Yuan

The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes.

Crowd Counting

PCC Net: Perspective Crowd Counting via Spatial Convolutional Network

1 code implementation24 May 2019 Junyu. Gao, Qi. Wang, Xuelong. Li

Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion.

Crowd Counting

Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification

no code implementations7 May 2019 Qi. Wang, Xiange He, Xuelong. Li

In this paper, a novel locality and structure regularized low rank representation (LSLRR) model is proposed for HSI classification.

General Classification Hyperspectral Image Classification

GETNET: A General End-to-end Two-dimensional CNN Framework for Hyperspectral Image Change Detection

no code implementations5 May 2019 Qi. Wang, Senior Member, Zhenghang Yuan, Qian Du, Xuelong. Li, Fellow, IEEE

In order to better handle high dimension problem and explore abundance information, this paper presents a General End-to-end Two-dimensional CNN (GETNET) framework for hyperspectral image change detection (HSI-CD).

Change Detection

A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling

no code implementations5 May 2019 Qi. Wang, Junyu. Gao, Yuan Yuan

Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; (2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; (3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time.

Autonomous Driving Data Augmentation +2

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

no code implementations5 May 2019 Yuan Yuan, Zhitong Xiong, Student Member, Qi. Wang, Senior Member, IEEE

Our contributions are as follows: 1) We propose a multi-resolution feature fusion network architecture which exploits densely connected deconvolution layers with skip connections, and can learn more effective features for the small size object; 2) We frame the traffic sign detection as a spatial sequence classification and regression task, and propose a vertical spatial sequence attention (VSSA) module to gain more context information for better detection performance.

Frame Object Detection +1

Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles

no code implementations5 May 2019 Chengze Wang, Yuan Yuan, Qi. Wang

In this paper, we present iDVO (inertia-embedded deep visual odometry), a self-supervised learning based monocular visual odometry (VO) for road vehicles.

Monocular Visual Odometry Self-Supervised Learning

Memory-Augmented Temporal Dynamic Learning for Action Recognition

no code implementations30 Apr 2019 Yuan Yuan, Dong Wang, Qi. Wang

Human actions captured in video sequences contain two crucial factors for action recognition, i. e., visual appearance and motion dynamics.

Action Recognition

Optimal Clustering Framework for Hyperspectral Band Selection

no code implementations30 Apr 2019 Qi. Wang, Fahong Zhang, Xuelong. Li

Band selection, by choosing a set of representative bands in hyperspectral image (HSI), is an effective method to reduce the redundant information without compromising the original contents.

Cross-Modal Message Passing for Two-stream Fusion

no code implementations30 Apr 2019 Dong Wang, Yuan Yuan, Qi. Wang

The classification object ensures that each modal network predicts the true action category while the competing objective encourages each modal network to outperform the other one.

Action Recognition General Classification +1

Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction

no code implementations30 Apr 2019 Yuan Yuan, Dong Wang, Qi. Wang

3) Results of motion orientation and magnitude are adaptively weighted and fused by a Bayesian model, which makes the proposed method more robust and handle more kinds of abnormal events.

Anomaly Detection Autonomous Vehicles

Early Action Prediction with Generative Adversarial Networks

no code implementations30 Apr 2019 Dong Wang, Yuan Yuan, Qi. Wang

Action Prediction is aimed to determine what action is occurring in a video as early as possible, which is crucial to many online applications, such as predicting a traffic accident before it happens and detecting malicious actions in the monitoring system.

Forward Vehicle Collision Warning Based on Quick Camera Calibration

no code implementations22 Apr 2019 Yuwei Lu, Yuan Yuan, Qi. Wang

Forward Vehicle Collision Warning (FCW) is one of the most important functions for autonomous vehicles.

Autonomous Vehicles Camera Calibration

Tracking as A Whole: Multi-Target Tracking by Modeling Group Behavior with Sequential Detection

no code implementations22 Apr 2019 Yuan Yuan, Yuwei Lu, Qi. Wang

In the detection stage, we present a sequential detection model to deal with serious occlusions.

Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes

no code implementations19 Apr 2019 Qi. Wang, Junyu. Gao, Xuelong. Li

In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks.

Domain Adaptation Semantic Segmentation

Listen to the Image

no code implementations CVPR 2019 Di Hu, Dong Wang, Xuelong. Li, Feiping Nie, Qi. Wang

different encoding schemes indicate that using machine model to accelerate optimization evaluation and reduce experimental cost is feasible to some extent, which could dramatically promote the upgrading of encoding scheme then help the blind to improve their visual perception ability.

Translation

Linking plastic heterogeneity of bulk metallic glasses to quench-in structural defects with machine learning

no code implementations7 Apr 2019 Qi. Wang, Anubhav Jain

When metallic glasses are subjected to mechanical loads, the plastic response of atoms is heterogeneous.

Materials Science Computational Physics

Learning from Synthetic Data for Crowd Counting in the Wild

no code implementations CVPR 2019 Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan

Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations.

Crowd Counting Domain Adaptation

Deep Bayesian Multi-Target Learning for Recommender Systems

no code implementations25 Feb 2019 Qi. Wang, Zhihui Ji, Huasheng Liu, Binqiang Zhao

This work introduces a multi-target optimization framework with Bayesian modeling of the target events, called Deep Bayesian Multi-Target Learning (DBMTL).

Model Selection Recommendation Systems

VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm for Model-based Control

no code implementations24 Dec 2018 Xingxing Liang, Qi. Wang, Yanghe Feng, Zhong Liu, Jincai Huang

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks.

Deep Attention Model-based Reinforcement Learning +1

PatientEG Dataset: Bringing Event Graph Model with Temporal Relations to Electronic Medical Records

no code implementations24 Dec 2018 Xuli Liu, Jihao Jin, Qi. Wang, Tong Ruan, Yangming Zhou, Daqi Gao, Yichao Yin

Based on the proposed model, we also construct a PatientEG dataset with 191, 294 events, 3, 429 distinct entities, and 545, 993 temporal relations using EMRs from Shanghai Shuguang hospital.

SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images

no code implementations30 Oct 2018 Han Liu, Lei Wang, Yandong Nan, Faguang Jin, Qi. Wang, Jiantao Pu

Two CNN-based classification models were then used as feature extractors to obtain the discriminative features of the entire CXR images and the cropped lung region images.

14 General Classification +1

DT-LET: Deep Transfer Learning by Exploring where to Transfer

no code implementations23 Sep 2018 Jianzhe Lin, Qi. Wang, Rabab Ward, Z. Jane Wang

Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains.

Transfer Learning

Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions

no code implementations27 Aug 2018 Jiahui Qiu, Qi. Wang, Yangming Zhou, Tong Ruan, Ju Gao

In this paper, we propose a Residual Dilated Convolutional Neural Network with Conditional Random Field (RD-CNN-CRF) to solve it.

Named Entity Recognition Translation

An attention-based Bi-GRU-CapsNet model for hypernymy detection between compound entities

1 code implementation13 May 2018 Qi. Wang, Chenming Xu, Yangming Zhou, Tong Ruan, Daqi Gao, Ping He

In this paper, we present an attention-based Bi-GRU-CapsNet model to detect hypernymy relationship between compound entities.

Incorporating Dictionaries into Deep Neural Networks for the Chinese Clinical Named Entity Recognition

no code implementations13 Apr 2018 Qi. Wang, Yuhang Xia, Yangming Zhou, Tong Ruan, Daqi Gao, Ping He

Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research.

Feature Engineering Named Entity Recognition

From Maxout to Channel-Out: Encoding Information on Sparse Pathways

no code implementations18 Nov 2013 Qi. Wang, Joseph JaJa

Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks.

General Classification Image Classification

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