Search Results for author: Feng Jiang

Found 31 papers, 8 papers with code

基于新闻图式结构的篇章功能语用识别方法(Discourse Functional Pragmatics Recognition Based on News Schemata)

no code implementations CCL 2022 Mengqi Du, Feng Jiang, Xiaomin Chu, Peifeng Li

“篇章分析是自然语言处理领域的研究热点和重点, 篇章功能语用研究旨在分析篇章单元在篇章中的功能和作用, 有助于深入理解篇章的主题和内容。目前篇章分析研究以形式语法为主, 而篇章作为一个整体的语义单位, 其功能和语义却没有引起足够重视。已有功能语用研究以面向事件抽取任务为主, 并未进行通用领域的功能语用研究。鉴于功能语用研究的重要性和研究现状, 本文提出了基于新闻图式结构的篇章功能语用识别方法来识别篇章功能语用。该方法在获取段落交互信息的同时又融入了篇章的新闻图式结构信息, 并结合段落所在篇章中的位置信息, 从而有效地提高了篇章功能语用的识别能力。在汉语宏观篇章树库的实验结果证明, 本文提出的方法优于所有基准系统。”

Automated Chinese Essay Scoring from Multiple Traits

no code implementations COLING 2022 Yaqiong He, Feng Jiang, Xiaomin Chu, Peifeng Li

Automatic Essay Scoring (AES) is the task of using the computer to evaluate the quality of essays automatically.

Key Mention Pairs Guided Document-Level Relation Extraction

no code implementations COLING 2022 Feng Jiang, Jianwei Niu, Shasha Mo, Shengda Fan

To this end, we propose a novel DocRE model called Key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier.

Document-level Relation Extraction

Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm

1 code implementation28 Feb 2023 Yan Shu, Shaohui Liu, Honglei Xu, Feng Jiang

Recently, developing an automatic reading system for analog measuring instruments has gained increased attention, as it enables the collection of numerous state of equipment.

Image Compressed Sensing Using Non-local Neural Network

1 code implementation7 Dec 2021 Wenxue Cui, Shaohui Liu, Feng Jiang, Debin Zhao

In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality.

Image Compressed Sensing

Residual Relaxation for Multi-view Representation Learning

no code implementations NeurIPS 2021 Yifei Wang, Zhengyang Geng, Feng Jiang, Chuming Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation.

Data Augmentation Representation Learning

Detecting and Correcting IMU Movements During Joint Angle Estimation

no code implementations9 Jun 2021 Chunzhi Yi, Feng Jiang, Baichun Wei, Chifu Yang, Zhen Ding, Jubo Jin, Jie Liu

The results demonstrate our method is a promising solution to detecting and correcting IMU movements during JAE.

Continuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals

no code implementations22 Mar 2021 Chunzhi Yi, Feng Jiang, Shengping Zhang, Hao Guo, Chifu Yang, Zhen Ding, Baichun Wei, Xiangyuan Lan, Huiyu Zhou

Challenges of exoskeletons motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission.

Multi-Stage Residual Hiding for Image-into-Audio Steganography

no code implementations6 Jan 2021 Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao

The widespread application of audio communication technologies has speeded up audio data flowing across the Internet, which made it a popular carrier for covert communication.

Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading

no code implementations COLING 2020 Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu

Discourse structure tree construction is the fundamental task of discourse parsing and most previous work focused on English.

Discourse Parsing

Hierarchical Complementary Learning for Weakly Supervised Object Localization

no code implementations16 Nov 2020 Sabrina Narimene Benassou, Wuzhen Shi, Feng Jiang, Abdallah Benzine

The aim of removing parts from image or detected parts of the object is to force the model to detect the other features.

Weakly-Supervised Object Localization

Entropy Guided Adversarial Model for Weakly Supervised Object Localization

no code implementations4 Aug 2020 Sabrina Narimene Benassou, Wuzhen Shi, Feng Jiang

Unfortunately, the network activates only the features that discriminate the object and does not activate the whole object.

Weakly-Supervised Object Localization

Deep-VFX: Deep Action Recognition Driven VFX for Short Video

no code implementations22 Jul 2020 Ao Luo, Ning Xie, Zhijia Tao, Feng Jiang

In the application, short-form mobile video is so popular all over the world such as Tik Tok.

Action Recognition Template Matching

Improving Entity Linking by Modeling Latent Entity Type Information

no code implementations6 Jan 2020 Shuang Chen, Jinpeng Wang, Feng Jiang, Chin-Yew Lin

Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility.

Ranked #2 on Entity Disambiguation on AIDA-CoNLL (Micro-F1 metric)

Entity Disambiguation Entity Embeddings +2

On Compression of Unsupervised Neural Nets by Pruning Weak Connections

1 code implementation21 Jan 2019 Zhiwen Zuo, Lei Zhao, Liwen Zuo, Feng Jiang, Wei Xing, Dongming Lu

Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction, unsupervised weight initialization and density estimation.

Density Estimation

Convolutional Neural Networks based Intra Prediction for HEVC

no code implementations17 Aug 2018 Wenxue Cui, Tao Zhang, Shengping Zhang, Feng Jiang, WangMeng Zuo, Debin Zhao

To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.

MCDTB: A Macro-level Chinese Discourse TreeBank

no code implementations COLING 2018 Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus.

Reading Comprehension

Deep neural network based sparse measurement matrix for image compressed sensing

1 code implementation19 Jun 2018 Wenxue Cui, Feng Jiang, Xinwei Gao, Wen Tao, Debin Zhao

In this paper, a Deep neural network based Sparse Measurement Matrix (DSMM) is learned by the proposed convolutional network to reduce the sampling computational complexity and improve the CS reconstruction performance.

Image Compressed Sensing

An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios

1 code implementation13 Apr 2018 Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao

To address this problem, we propose a deep convolutional Laplacian Pyramid Compressed Sensing Network (LapCSNet) for CS, which consists of a sampling sub-network and a reconstruction sub-network.

Compressive Sensing Image Compression

An End-to-End Compression Framework Based on Convolutional Neural Networks

5 code implementations2 Aug 2017 Feng Jiang, Wen Tao, Shaohui Liu, Jie Ren, Xun Guo, Debin Zhao

The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high-quality in the decoding end.

Denoising Image Compression

Deep Networks for Compressed Image Sensing

no code implementations22 Jul 2017 Wuzhen Shi, Feng Jiang, Shengping Zhang, Debin Zhao

First of all, we train a sampling matrix via the network training instead of using a traditional manually designed one, which is much appropriate for our deep network based reconstruct process.

Image Compression

Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module

2 code implementations22 Jul 2017 Wuzhen Shi, Feng Jiang, Debin Zhao

With the novel dilated convolution based inception module, the proposed end-to-end single image super-resolution network can take advantage of multi-scale information to improve image super-resolution performance.

Image Restoration Image Super-Resolution

Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition

no code implementations29 Jan 2015 Qi Guo, Bo-Wei Chen, Feng Jiang, Xiangyang Ji, Sun-Yuan Kung

Firstly, we divide the feature space into several subspaces using the decomposition method proposed in this paper.

Classification General Classification

Spatially Directional Predictive Coding for Block-based Compressive Sensing of Natural Images

no code implementations29 Apr 2014 Jian Zhang, Debin Zhao, Feng Jiang

At the encoder, for each block of compressive sensing (CS) measurements, the optimal pre-diction is selected from a set of prediction candidates that are generated by four designed directional predictive modes.

Compressive Sensing

Structural Group Sparse Representation for Image Compressive Sensing Recovery

no code implementations29 Apr 2014 Jian Zhang, Debin Zhao, Feng Jiang, Wen Gao

Compressive Sensing (CS) theory shows that a signal can be decoded from many fewer measurements than suggested by the Nyquist sampling theory, when the signal is sparse in some domain.

Compressive Sensing

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