Search Results for author: Ying Chen

Found 61 papers, 26 papers with code

Spot-adaptive Knowledge Distillation

1 code implementation5 May 2022 Jie Song, Ying Chen, Jingwen Ye, Mingli Song

Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks.

Knowledge Distillation

AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement

1 code implementation29 Apr 2022 Canqian Yang, Meiguang Jin, Xu Jia, Yi Xu, Ying Chen

They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform.

Image Enhancement

Progressive Training of A Two-Stage Framework for Video Restoration

1 code implementation21 Apr 2022 Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen

As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts.

Frame Transfer Learning +2

Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation

no code implementations5 Apr 2022 Zhengyang Lu, Ying Chen

In this work, a Pyramid Frequency Network(PFN) with Spatial Attention Residual Refinement Module(SARRM) is proposed to deal with the weak robustness of existing deep-learning methods.

Monocular Depth Estimation

An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development

no code implementations25 Mar 2022 Jin Yang, Yingying Huang, Guangxin Jiang, Ying Chen

In the first component, we introduce a theoretical function-preserving transformation of recurrent neural networks (RNN) to the literature for capturing the hidden temporal patterns within the time-series data.

Neural Architecture Search Time Series

DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine

2 code implementations19 Mar 2022 Yifu Qiu, Hongyu Li, Yingqi Qu, Ying Chen, Qiaoqiao She, Jing Liu, Hua Wu, Haifeng Wang

To ensure the quality of our benchmark and address the shortcomings in other existing datasets, we (1) reduce the false negatives in development and testing sets by pooling the results from multiple retrievers with human annotations, (2) and remove the semantically similar questions between training with development and testing sets.

Domain Generalization Passage Retrieval

Applications of blockchain and artificial intelligence technologies for enabling prosumers in smart grids: A review

no code implementations21 Feb 2022 Weiqi Hua, Ying Chen, Meysam Qadrdan, Jing Jiang, Hongjian Sun, Jianzhong Wu

The blockchain and artificial intelligence (AI) are innovative technologies to fulfil these two factors, by which the blockchain provides decentralised trading platforms for energy markets and the AI supports the optimal operational control of power systems.

Decision Making

Guide Local Feature Matching by Overlap Estimation

1 code implementation18 Feb 2022 Ying Chen, Dihe Huang, Shang Xu, Jianlin Liu, Yong liu

Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important.

VR Viewport Pose Model for Quantifying and Exploiting Frame Correlations

1 code implementation11 Jan 2022 Ying Chen, Hojung Kwon, Hazer Inaltekin, Maria Gorlatova

The importance of the dynamics of the viewport pose, i. e., the location and the orientation of users' points of view, for virtual reality (VR) experiences calls for the development of VR viewport pose models.


DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models

1 code implementation16 Dec 2021 Hongyu Zhu, Yan Chen, Jing Yan, Jing Liu, Yu Hong, Ying Chen, Hua Wu, Haifeng Wang

For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models.

Feasibility Study of Neural ODE and DAE Modules for Power System Dynamic Component Modeling

2 code implementations25 Oct 2021 Tannan Xiao, Ying Chen, Shaowei Huang, Tirui He, Huizhe Guan

In the context of high penetration of renewables and power electronics, the need to build dynamic models of power system components based on accessible measurement data has become urgent.

Numerical Integration

Semi-supervised Domain Adaptation for Semantic Segmentation

no code implementations20 Oct 2021 Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam

We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.

Data Augmentation Semantic Segmentation +1

Exploration of AI-Oriented Power System Dynamic Simulations

2 code implementations3 Oct 2021 Tannan Xiao, Ying Chen, Jianquan Wang, Shaowei Huang, Weilin Tong, Tirui He

With the rapid development of Artificial Intelligence (AI), it is foreseeable that the accuracy and efficiency of future power system dynamic analysis will be greatly improved by the integration of dynamic simulators and AI.

Multi-Modal Sarcasm Detection Based on Contrastive Attention Mechanism

1 code implementation30 Sep 2021 Xiaoqiang Zhang, Ying Chen, Guangyuan Li

In the past decade, sarcasm detection has been intensively conducted in a textual scenario.

Sarcasm Detection

DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation

no code implementations30 Aug 2021 Lijie Wang, Hao liu, Shuyuan Peng, Hongxuan Tang, Xinyan Xiao, Ying Chen, Hua Wu, Haifeng Wang

Therefore, in order to systematically evaluate the factors for building trustworthy systems, we propose a novel and well-annotated sentiment analysis dataset to evaluate robustness and interpretability.

Sentiment Analysis

Multi-granularity for knowledge distillation

1 code implementation15 Aug 2021 Baitan Shao, Ying Chen

Considering the fact that students have different abilities to understand the knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable knowledge for student networks.

Knowledge Distillation Person Re-Identification

Tree-Like Decision Distillation

no code implementations CVPR 2021 Jie Song, Haofei Zhang, Xinchao Wang, Mengqi Xue, Ying Chen, Li Sun, DaCheng Tao, Mingli Song

Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.

Decision Making Knowledge Distillation

Deep Switching State Space Model (DS$^3$M) for Nonlinear Time Series Forecasting with Regime Switching

no code implementations4 Jun 2021 Xiuqin Xu, Ying Chen

We propose a deep switching state space model (DS$^3$M) for efficient inference and forecasting of nonlinear time series with irregularly switching among various regimes.

Time Series Time Series Forecasting +1

Integrated Communication and Navigation for Ultra-Dense LEO Satellite Networks: Vision, Challenges and Solutions

no code implementations19 May 2021 Yu Wang, Hejia Luo, Ying Chen, Jun Wang, Rong Li, Bin Wang

Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner.

Spectral Machine Learning for Pancreatic Mass Imaging Classification

no code implementations3 May 2021 Yiming Liu, Ying Chen, Guangming Pan, Weichung Wang, Wei-Chih Liao, Yee Liang Thian, Cheng E. Chee, Constantinos P. Anastassiades

Factors that influenced high performance of a well-designed integration of spectral learning and machine learning included: 1) use of eigenvectors corresponding to several of the largest eigenvalues of sample covariance matrix (spike eigenvectors) to choose input attributes in classification training, taking into account only the fundamental information of the raw images with less noise; 2) removal of irrelevant pixels based on mean-level spectral test to lower the challenges of memory capacity and enhance computational efficiency while maintaining superior classification accuracy; 3) adoption of state-of-the-art machine learning classification, gradient boosting and random forest.

Classification General Classification

Refining Language Models with Compositional Explanations

1 code implementation NeurIPS 2021 Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, Xiang Ren

However, such a regularization technique lacks flexibility and coverage, since only importance scores towards a pre-defined list of features are adjusted, while more complex human knowledge such as feature interaction and pattern generalization can hardly be incorporated.

Fairness Language Modelling +1

Deep Stochastic Volatility Model

1 code implementation25 Feb 2021 Xiuqin Xu, Ying Chen

We propose a deep stochastic volatility model (DSVM) based on the framework of deep latent variable models.

Variational Inference

The Variational Bayesian Inference for Network Autoregression Models

no code implementations18 Feb 2021 Wei-Ting Lai, Ray-Bing Chen, Ying Chen, Thorsten Koch

We develop a variational Bayesian (VB) approach for estimating large-scale dynamic network models in the network autoregression framework.

Bayesian Inference

Exclusive Topic Modeling

no code implementations6 Feb 2021 Hao Lei, Ying Chen

We propose an Exclusive Topic Modeling (ETM) for unsupervised text classification, which is able to 1) identify the field-specific keywords though less frequently appeared and 2) deliver well-structured topics with exclusive words.

Text Classification

Concentrated Document Topic Model

no code implementations6 Feb 2021 Hao Lei, Ying Chen

We propose a Concentrated Document Topic Model(CDTM) for unsupervised text classification, which is able to produce a concentrated and sparse document topic distribution.

Text Classification

Mask-based Data Augmentation for Semi-supervised Semantic Segmentation

no code implementations25 Jan 2021 Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam

Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive.

Data Augmentation Semi-Supervised Semantic Segmentation

Self-Born Wiring for Neural Trees

no code implementations ICCV 2021 Ying Chen, Feng Mao, Jie Song, Xinchao Wang, Huiqiong Wang, Mingli Song

Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.

Representation Learning

MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

1 code implementation8 Dec 2020 Liang Qiao, Ying Chen, Zhanzhan Cheng, Yunlu Xu, Yi Niu, ShiLiang Pu, Fei Wu

Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications.

Text Spotting

Domain Adaptation on Semantic Segmentation for Aerial Images

no code implementations3 Dec 2020 Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam

In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation.

Semantic Segmentation Unsupervised Domain Adaptation

End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network

1 code implementation COLING 2020 Ying Chen, Wenjun Hou, Shoushan Li, Caicong Wu, Xiaoqiang Zhang

Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages.

Emotion Cause Pair Extraction Emotion-Cause Pair Extraction

Cascade Attentive Dropout for Weakly Supervised Object Detection

no code implementations20 Nov 2020 Wenlong Gao, Ying Chen, Yong Peng

Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision.

Multiple Instance Learning Weakly Supervised Object Detection

Dense U-net for super-resolution with shuffle pooling layer

no code implementations11 Nov 2020 Zhengyang Lu, Ying Chen

By doing so, we effectively replace the handcrafted filter in the SISR pipeline with more lossy down-sampling filters specifically trained for each feature map, whilst also reducing the information loss of the overall SISR operation.

Image Super-Resolution SSIM

DEAL: Difficulty-aware Active Learning for Semantic Segmentation

1 code implementation17 Oct 2020 Shuai Xie, Zunlei Feng, Ying Chen, Songtao Sun, Chao Ma, Mingli Song

To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch.

Active Learning Semantic Segmentation

Regularised Text Logistic Regression: Key Word Detection and Sentiment Classification for Online Reviews

no code implementations9 Sep 2020 Ying Chen, Peng Liu, Chung Piaw Teo

Moreover, RTL identifies a small set of word features, corresponding to 3% for Restaurant and 20% for Hotel, which boosts working efficiency by allowing managers to drill down into a much smaller set of important customer reviews.

Classification General Classification +1

Probabilistic Forecasting for Daily Electricity Loads and Quantiles for Curve-to-Curve Regression

1 code implementation3 Sep 2020 Xiuqin Xu, Ying Chen, Yannig Goude, Qiwei Yao

When applying to one day ahead forecasting for the French daily electricity load curves, PPC outperform several state-of-the-art predictive methods in terms of forecasting accuracy, coverage rate and average length of the predictive bands.

Methodology Applications

Automatic Crack Detection on Road Pavements Using Encoder Decoder Architecture

no code implementations1 Jul 2020 Zhun Fan, Chong Li, Ying Chen, Jiahong Wei, Giuseppe Loprencipe, Xiaopeng Chen, Paola Di Mascio

Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low-level convolutional layers, which are integrated to predict pixel-wise crack detection.

Object Detection

DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC

1 code implementation23 Jun 2020 Tianyi Li, Mai Xu, Runzhi Tang, Ying Chen, Qunliang Xing

In VVC, the quad-tree plus multi-type tree (QTMT) structure of coding unit (CU) partition accounts for over 97% of the encoding time, due to the brute-force search for recursive rate-distortion (RD) optimization.

DO-Conv: Depthwise Over-parameterized Convolutional Layer

1 code implementation22 Jun 2020 Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu

Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.

Image Classification

Two-stage short-term wind power forecasting algorithm using different feature-learning models

no code implementations31 May 2020 Jiancheng Qin, Jin Yang, Ying Chen, Qiang Ye, Hua Li

Considering the overfitting issue, we propose a new moving window-based algorithm using a validation set in the first stage to update the training data in both stages with two different moving window processes. Experiments were conducted at three wind farms, and the results demonstrate that the model with single input multiple output structure obtains better forecasting accuracy compared to existing models.

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

1 code implementation27 May 2020 Zhuoying Wang, Yongtao Wang, Zhi Tang, Yangyan Li, Ying Chen, Haibin Ling, Weisi Lin

Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.

Pose Estimation Semantic Segmentation

Stochastic Sparse Subspace Clustering

no code implementations CVPR 2020 Ying Chen, Chun-Guang Li, Chong You

State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points.

Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement

no code implementations8 Feb 2020 Zhun Fan, Chong Li, Ying Chen, Paola Di Mascio, Xiaopeng Chen, Guijie Zhu, Giuseppe Loprencipe

In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement.

MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion

no code implementations19 Jan 2020 Kaiyu Shan, Yongtao Wang, Zhuoying Wang, TingTing Liang, Zhi Tang, Ying Chen, Yangyan Li

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.

Action Recognition

MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?

1 code implementation16 Jan 2020 Joseph Bethge, Christian Bartz, Haojin Yang, Ying Chen, Christoph Meinel

However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks.


Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data

no code implementations17 Dec 2019 Shibo Zhou, Ying Chen, Xiaohua LI, Arindam Sanyal

In this paper, we integrate spiking convolutional neural network (SCNN) with temporal coding into the YOLOv2 architecture for real-time object detection.

3D Object Detection Real-Time Object Detection +1

Portfolio liquidation under transient price impact -- theoretical solution and implementation with 100 NASDAQ stocks

no code implementations13 Dec 2019 Ying Chen, Ulrich Horst, Hoang Hai Tran

We derive an explicit solution for deterministic market impact parameters in the Graewe and Horst (2017) portfolio liquidation model.

Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss

no code implementations21 Nov 2019 Zhengyang Lu, Ying Chen

To solve this problem, the mixed gradient error, which is composed by MSE and a weighted mean gradient error, is proposed in this work and applied to a modified U-net network as the loss function.

Image Super-Resolution

CAUnLP at NLP4IF 2019 Shared Task: Context-Dependent BERT for Sentence-Level Propaganda Detection

no code implementations WS 2019 Wenjun Hou, Ying Chen

This paper presents the sys- tem of our participation in the sentence-level subtask of the propaganda detection shared task.

Propaganda detection

Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance

1 code implementation24 Sep 2019 Shibo Zhou, Xiaohua LI, Ying Chen, Sanjeev T. Chandrasekaran, Arindam Sanyal

Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency.

Data Augmentation Object Recognition

Where does active travel fit within local community narratives of mobility space and place?

no code implementations7 May 2019 Alec Biehl, Ying Chen, Karla Sanabria-Veaz, David Uttal, Amanda Stathopoulos

The analysis uncovers the local mobility culture, embedded norms and values associated with acceptance of active travel modes in different communities.

Sentiment Analysis

Segmentation of Levator Hiatus Using Multi-Scale Local Region Active contours and Boundary Shape Similarity Constraint

no code implementations11 Jan 2019 Xinling Zhang, Xu Li, Ying Chen, Yixin Gan, Dexing Kong, Rongqin Zheng

In this paper, a multi-scale framework with local region based active contour and boundary shape similarity constraint is proposed for the segmentation of levator hiatus in ultrasound images.

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

6 code implementations12 Nov 2018 Qijie Zhao, Tao Sheng, Yongtao Wang, Zhi Tang, Ying Chen, Ling Cai, Haibin Ling

Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels.

Object Detection

Joint Learning for Emotion Classification and Emotion Cause Detection

no code implementations EMNLP 2018 Ying Chen, Wenjun Hou, Xiyao Cheng, Shoushan Li

We present a neural network-based joint approach for emotion classification and emotion cause detection, which attempts to capture mutual benefits across the two sub-tasks of emotion analysis.

Classification Emotion Classification +2

C-arm Tomographic Imaging Technique for Nephrolithiasis and Detection of Kidney Stones

no code implementations8 Jun 2017 Nuhad A. Malalla, Ying Chen

Our C-arm tomographic technique provides a series of two dimensional (2D) images with a single scan over 40o view angle.

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