Search Results for author: Qi Wang

Found 56 papers, 12 papers with code

Collaborative World Models: An Online-Offline Transfer RL Approach

no code implementations24 May 2023 Qi Wang, Junming Yang, Yunbo Wang, Xin Jin, Wenjun Zeng, Xiaokang Yang

Training visual reinforcement learning (RL) models in offline datasets is challenging due to overfitting issues in representation learning and overestimation problems in value function.

Reinforcement Learning (RL) Representation Learning +1

Large Language Models can be Guided to Evade AI-Generated Text Detection

no code implementations18 May 2023 Ning Lu, Shengcai Liu, Rui He, Qi Wang, Ke Tang

Large Language Models (LLMs) have demonstrated exceptional performance in a variety of tasks, including essay writing and question answering.

Question Answering

Dragon-Alpha&cu32: A Java-based Tensor Computing Framework With its High-Performance CUDA Library

no code implementations15 May 2023 Zhiyi Zhang, Pengfei Zhang, Qi Wang

Java is very powerful, but in Deep Learning field, its capabilities probably has not been sufficiently exploited.

Generic and Robust Root Cause Localization for Multi-Dimensional Data in Online Service Systems

1 code implementation5 May 2023 Zeyan Li, Junjie Chen, Yihao Chen, Chengyang Luo, Yiwei Zhao, Yongqian Sun, Kaixin Sui, Xiping Wang, Dapeng Liu, Xing Jin, Qi Wang, Dan Pei

Such attribute combinations are substantial clues to the underlying root causes and thus are called root causes of multidimensional data.

A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems

no code implementations28 Apr 2023 Frank E. Curtis, Vyacheslav Kungurtsev, Daniel P. Robinson, Qi Wang

A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function (that may be nonconvex) subject to bound constraints is presented, analyzed, and demonstrated through experimental results.

Improving Urban Flood Prediction using LSTM-DeepLabv3+ and Bayesian Optimization with Spatiotemporal feature fusion

no code implementations19 Apr 2023 Zuxiang Situ, Qi Wang, Shuai Teng, Wanen Feng, Gongfa Chen, Qianqian Zhou, Guangtao Fu

This study presented a CNN-RNN hybrid feature fusion modelling approach for urban flood prediction, which integrated the strengths of CNNs in processing spatial features and RNNs in analyzing different dimensions of time sequences.

Bayesian Optimization

Regularized Shallow Image Prior for Electrical Impedance Tomography

no code implementations30 Mar 2023 Zhe Liu, Zhou Chen, Qi Wang, Sheng Zhang, Yunjie Yang

The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.

Boundary-to-Solution Mapping for Groundwater Flows in a Toth Basin

no code implementations28 Mar 2023 Jingwei Sun, Jun Li, Yonghong Hao, Cuiting Qi, Chunmei Ma, Huazhi Sun, Negash Begashaw, Gurcan Comet, Yi Sun, Qi Wang

In this paper, the authors propose a new approach to solving the groundwater flow equation in the Toth basin of arbitrary top and bottom topographies using deep learning.

A Three-Player GAN for Super-Resolution in Magnetic Resonance Imaging

no code implementations24 Mar 2023 Qi Wang, Lucas Mahler, Julius Steiglechner, Florian Birk, Klaus Scheffler, Gabriele Lohmann

Current SISR methods for 3D volumetric images are based on Generative Adversarial Networks (GANs), especially Wasserstein GANs due to their training stability.

Image Super-Resolution

A Spatio-temporal Decomposition Method for the Coordinated Economic Dispatch of Integrated Transmission and Distribution Grids

no code implementations17 Mar 2023 Qi Wang, Wenchuan Wu, Chenhui Lin, Bin Wang

In the spatial dimension, a multi-parametric programming projection based spatial decomposition algorithm is developed to coordinate the ED problems of TG and DNs in a distributed manner.

Improving Video Retrieval by Adaptive Margin

no code implementations9 Mar 2023 Feng He, Qi Wang, Zhifan Feng, Wenbin Jiang, Yajuan Lv, Yong Zhu, Xiao Tan

While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue.

Retrieval Video Retrieval

Anomaly Detection of UAV State Data Based on Single-class Triangular Global Alignment Kernel Extreme Learning Machine

no code implementations18 Feb 2023 Feisha Hu, Qi Wang, Haijian Shao, Shang Gao, Hualong Yu

To improve the performance of OCKELM, we choose a Triangular Global Alignment Kernel (TGAK) instead of an RBF Kernel and introduce the Fast Independent Component Analysis (FastICA) algorithm to reconstruct UAV data.

Anomaly Detection

Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend

no code implementations6 Feb 2023 Ning Lu, Shengcai Liu, Zhirui Zhang, Qi Wang, Haifeng Liu, Ke Tang

Intuitively, this finding suggests a natural way to improve model robustness by training the model on the $n$-FD examples.

Adversarial Attack

RELIANT: Fair Knowledge Distillation for Graph Neural Networks

1 code implementation3 Jan 2023 Yushun Dong, Binchi Zhang, Yiling Yuan, Na Zou, Qi Wang, Jundong Li

Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i. e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i. e., the teacher GNN model).

Fairness Graph Learning +1

Towards Stable Human Pose Estimation via Cross-View Fusion and Foot Stabilization

no code implementations CVPR 2023 Li’an Zhuo, Jian Cao, Qi Wang, Bang Zhang, Liefeng Bo

Then the optimization-based method is introduced to reconstruct the foot pose and foot-ground contact for the general multi-view datasets including AIST++ and Human3. 6M.

Pose Estimation

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

1 code implementation5 Dec 2022 Qi Wang, Sheng Shi, Jiahui Li, Wuming Jiang, Xiangde Zhang

Existing methods are limited by the inconsistent point densities of different parts in the point cloud.

Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects

no code implementations2 Dec 2022 Qi Wang, Juncheng Wang, Junyu Gao, Yuan Yuan, Xuelong Li

The mainstream crowd counting methods regress density map and integrate it to obtain counting results.

Crowd Counting

Growing Instance Mask on Leaf

no code implementations30 Nov 2022 Chuang Yang, Haozhao Ma, Qi Wang

Considering the superiorities above, we propose VeinMask to formulate the instance segmentation problem as the simulation of the vein growth process and to predict the major and minor veins in polar coordinates.

Instance Segmentation Semantic Segmentation

MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting

no code implementations14 Aug 2022 PengYu Chen, Junyu Gao, Yuan Yuan, Qi Wang

RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RGB-based methods in scenes with low-illumination or similar backgrounds.

Crowd Counting

Physics-informed Deep Super-resolution for Spatiotemporal Data

1 code implementation2 Aug 2022 Pu Ren, Chengping Rao, Yang Liu, Zihan Ma, Qi Wang, Jian-Xun Wang, Hao Sun

High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales.


SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network

no code implementations9 Jul 2022 Qi Wang, Jingwu Mei

This paper proposes an industrial weld segmentation network based on a deep learning semantic segmentation algorithm fused with heatmap detail guidance and Image Matting to solve the automatic segmentation problem of weld regions.

Image Matting Semantic Segmentation

Holistic Transformer: A Joint Neural Network for Trajectory Prediction and Decision-Making of Autonomous Vehicles

no code implementations17 Jun 2022 Hongyu Hu, Qi Wang, Zhengguang Zhang, Zhengyi Li, Zhenhai Gao

Trajectory prediction and behavioral decision-making are two important tasks for autonomous vehicles that require good understanding of the environmental context; behavioral decisions are better made by referring to the outputs of trajectory predictions.

Autonomous Vehicles Decision Making +2

Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher

no code implementations12 Jun 2022 Juncheng Wang, Junyu Gao, Yuan Yuan, Qi Wang

The core reason of intrinsic scale shift being one of the most essential issues in crowd localization is that it is ubiquitous in crowd scenes and makes scale distribution chaotic.

Optimization-based Block Coordinate Gradient Coding for Mitigating Partial Stragglers in Distributed Learning

no code implementations6 Jun 2022 Qi Wang, Ying Cui, Chenglin Li, Junni Zou, Hongkai Xiong

To reduce computational complexity, we first transform each to an equivalent but much simpler discrete problem with N\llL variables representing the partition of the L coordinates into N blocks, each with identical redundancy.

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

1 code implementation25 May 2022 Shuke Zhang, Yanzhao Jin, Tianmeng Liu, Qi Wang, Zhaohui Zhang, Shuliang Zhao, Bo Shan

We also develop an edge-based atom-pair feature aggregation method to represent complex interactions and a graph pooling-based method to predict the binding affinity of the complex.

DR.VIC: Decomposition and Reasoning for Video Individual Counting

1 code implementation CVPR 2022 Tao Han, Lei Bai, Junyu Gao, Qi Wang, Wanli Ouyang

Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame.

Crowd Counting Density Estimation +2

A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients

no code implementations21 Feb 2022 Zhijun Zeng, Zhen Hou, Ting Li, Lei Deng, Jianguo Hou, Xinran Huang, Jun Li, Meirou Sun, Yunhan Wang, Qiyu Wu, Wenhao Zheng, Hua Jiang, Qi Wang

We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model.

Towards Integrated Sensing and Communications for 6G

no code implementations12 Jan 2022 Qi Wang, Anastasios Kakkavas, Xitao Gong, Richard A. Stirling-Gallacher

For the next generation of mobile communications systems, the integration of sensing and communications promises benefits in terms of spectrum utilization, cost, latency, area and weight.

Adaptive Shrink-Mask for Text Detection

no code implementations18 Nov 2021 Chuang Yang, Mulin Chen, Yuan Yuan, Qi Wang, Xuelong Li

It weakens the coupling of texts to shrink-masks, which improves the robustness of detection results.

ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition

no code implementations14 Oct 2021 Zhitong Xiong, Yuan Yuan, Qi Wang

Discriminative local theme-level and object-level representations can be selected with the DLFS module from the spatially-correlated multi-modal RGB-D features.

feature selection Scene Classification +1

LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds

no code implementations10 Oct 2021 Qi Wang, Tao Han, Junyu Gao, Yuan Yuan, Xuelong Li

The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map.

Visual Crowd Analysis

Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification

no code implementations12 Sep 2021 Qi Wang, Sikai Bai, Junyu Gao, Yuan Yuan, Xuelong Li

In addition, due to domain gaps between different datasets, the performance is dramatically decreased when re-ID models pre-trained on label-rich datasets (source domain) are directly applied to other unlabeled datasets (target domain).

Person Re-Identification Unsupervised Domain Adaptation

Encoding physics to learn reaction-diffusion processes

2 code implementations9 Jun 2021 Chengping Rao, Pu Ren, Qi Wang, Oral Buyukozturk, Hao Sun, Yang Liu

Modeling complex spatiotemporal dynamical systems, such as the reaction-diffusion processes, have largely relied on partial differential equations (PDEs).


Waveform Design for Joint Sensing and Communications in Millimeter-Wave and Low Terahertz Bands

no code implementations3 Jun 2021 Tianqi Mao, Jiaxuan Chen, Qi Wang, Chong Han, Zhaocheng Wang, George K. Karagiannidis

Finally, a data-embedded MS-QP (DE-MS-QP) waveform is constructed through time-domain extension of the MS-QP sequence, generating null frequency points on each subband for data transmission.

MT: Multi-Perspective Feature Learning Network for Scene Text Detection

no code implementations12 May 2021 Chuang Yang, Mulin Chen, Yuan Yuan, Qi Wang

Text detection, the key technology for understanding scene text, has become an attractive research topic.

Scene Text Detection

Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image

no code implementations24 Apr 2021 Qi Wang, Yanling Miao, Mulin Chen, Xuelong Li

In order to better handle the high dimensionality problem and preserve the spatial structures, this paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering.

BiP-Net: Bidirectional Perspective Strategy based Arbitrary-Shaped Text Detection Network

no code implementations11 Apr 2021 Chuang Yang, Mulin Chen, Yuan Yuan, Qi Wang

Specifically, a new text representation strategy is proposed to represent text contours from a top-down perspective, which can fit highly curved text contours effectively.

Object Detection

Auto-weighted Multi-view Feature Selection with Graph Optimization

no code implementations11 Apr 2021 Qi Wang, Xu Jiang, Mulin Chen, Xuelong Li

In this paper, we focus on the unsupervised multi-view feature selection which tries to handle high dimensional data in the field of multi-view learning.

feature selection Graph Learning +1

Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning

no code implementations25 Mar 2021 Yanling Miao, Qi Wang, Mulin Chen, Xuelong Li

Graph-based semi-supervised learning methods, which deal well with the situation of limited labeled data, have shown dominant performance in practical applications.

Ensemble Learning General Classification +1

Multi-channel Deep Supervision for Crowd Counting

no code implementations17 Mar 2021 Bo Wei, Mulin Chen, Qi Wang, Xuelong Li

To obtain the accurate supervision information of different channels, the MDSNet employs an auxiliary network called SupervisionNet (SN) to generate abundant supervision maps based on existing groundtruth.

Crowd Counting

Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models

no code implementations16 Feb 2021 Qi Wang, Herke van Hoof

Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real-world applications.

Decision Making Meta Reinforcement Learning +3

Dynamics of a predator-prey system in open advective heterogeneous environments

no code implementations21 Dec 2020 Qi Wang

In this paper, we investigate the effect of dispersal and advection on the dynamics of a predator-prey model.

Analysis of PDEs 35B35, 35K57, 92D25, 92D40

Inverse-design magnonic devices

no code implementations8 Dec 2020 Qi Wang, Andrii V. Chumak, Philipp Pirro

The field of magnonics offers a new type of low-power information processing, in which magnons, the quanta of spin waves, carry and process data instead of electrons.

Applied Physics

Learning Independent Instance Maps for Crowd Localization

1 code implementation8 Dec 2020 Junyu Gao, Tao Han, Qi Wang, Yuan Yuan, Xuelong Li

Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps.


CM-Net: Concentric Mask based Arbitrary-Shaped Text Detection

no code implementations30 Nov 2020 Chuang Yang, Mulin Chen, Zhitong Xiong, Yuan Yuan, Qi Wang

Extensive experiments demonstrate the proposed CM is efficient and robust to fit arbitrary-shaped text instances, and also validate the effectiveness of MPF and constraints loss for discriminative text features recognition.

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

1 code implementation NeurIPS 2020 Tao Han, Junyu Gao, Yuan Yuan, Qi Wang

In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating.

Template Matching

Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance

no code implementations8 Dec 2019 Junyu. Gao, Yuan Yuan, Qi Wang

To reduce the gap, in this paper, we propose a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes.

Crowd Counting Density Estimation +1

QMR:Q-learning based Multi-objective optimization Routing protocol for Flying Ad Hoc Networks

1 code implementation Computer Communications 2019 Jianmin Liu, Qi Wang, ChenTao He, Katia Jaffrès-Runser, Yida Xu, Zhenyu Li, Yongjun Xu

It is difficult for existing routing protocols for Mobile Ad Hoc Networks (MANETs) and Vehicular Ad Hoc Networks (VANETs) to adapt the high dynamics of FANETs.


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