Search Results for author: Jun Hu

Found 14 papers, 2 papers with code

Adaptive Convolutions with Per-pixel Dynamic Filter Atom

no code implementations17 Aug 2021 Ze Wang, Zichen Miao, Jun Hu, Qiang Qiu

Applying feature dependent network weights have been proved to be effective in many fields.

VTLayout: Fusion of Visual and Text Features for Document Layout Analysis

no code implementations12 Aug 2021 Shoubin Li, Xuyan Ma, Shuaiqun Pan, Jun Hu, Lin Shi, Qing Wang

In the second stage, the deep visual, shallow visual, and text features are extracted for fusion to identify the category blocks of documents.

Document Layout Analysis

Feature-Align Network with Knowledge Distillation for Efficient Denoising

no code implementations2 Mar 2021 Lucas D. Young, Fitsum A. Reda, Rakesh Ranjan, Jon Morton, Jun Hu, Yazhu Ling, Xiaoyu Xiang, David Liu, Vikas Chandra

(2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss.

Image Denoising Image Restoration +1

Efficient Graph Deep Learning in TensorFlow with tf_geometric

1 code implementation27 Jan 2021 Jun Hu, Shengsheng Qian, Quan Fang, Youze Wang, Quan Zhao, Huaiwen Zhang, Changsheng Xu

We introduce tf_geometric, an efficient and friendly library for graph deep learning, which is compatible with both TensorFlow 1. x and 2. x.

Classification General Classification +5

Super strong paramagnetism of aromatic peptides adsorbed with monovalent cations

no code implementations22 Dec 2020 Shiqi Sheng, Haijun Yang, Liuhua Mu, Zixin Wang, Jihong Wang, Peng Xiu, Jun Hu, Xin Zhang, Feng Zhang, Haiping Fang

We experimentally demonstrated that the AYFFF self-assemblies adsorbed with various monovalent cations (Na+, K+, and Li+) show unexpectedly super strong paramagnetism.

Biological Physics

Fault Detection for Covered Conductors With High-Frequency Voltage Signals: From Local Patterns to Global Features

no code implementations1 Nov 2020 Kunjin Chen, Tomáš Vantuch, Yu Zhang, Jun Hu, Jinliang He

The detection and characterization of partial discharge (PD) are crucial for the insulation diagnosis of overhead lines with covered conductors.

Fault Detection

PEL-BERT: A Joint Model for Protocol Entity Linking

no code implementations28 Jan 2020 Shoubin Li, Wenzao Cui, Yujiang Liu, Xuran Ming, Jun Hu, YuanzheHu, Qing Wang

Pre-trained models such as BERT are widely used in NLP tasks and are fine-tuned to improve the performance of various NLP tasks consistently.

Entity Linking Language Modelling

Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring

no code implementations17 Nov 2019 Kunjin Chen, Yu Zhang, Qin Wang, Jun Hu, Hang Fan, Jinliang He

Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters.

Non-Intrusive Load Monitoring

Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks

no code implementations22 Dec 2018 Kunjin Chen, Jun Hu, Yu Zhang, Zhanqing Yu, Jinliang He

This paper develops a novel graph convolutional network (GCN) framework for fault location in power distribution networks.

Data Augmentation Data Visualization

Convolutional Sequence to Sequence Non-intrusive Load Monitoring

no code implementations6 Jun 2018 Kunjin Chen, Qin Wang, Ziyu He, Kunlong Chen, Jun Hu, Jinliang He

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper.

Non-Intrusive Load Monitoring

Short-term Load Forecasting with Deep Residual Networks

1 code implementation30 May 2018 Kunjin Chen, Kunlong Chen, Qin Wang, Ziyu He, Jun Hu, Jinliang He

We present in this paper a model for forecasting short-term power loads based on deep residual networks.

Load Forecasting

HDR Deghosting: How to Deal with Saturation?

no code implementations CVPR 2013 Jun Hu, Orazio Gallo, Kari Pulli, Xiaobai Sun

We present a novel method for aligning images in an HDR (high-dynamic-range) image stack to produce a new exposure stack where all the images are aligned and appear as if they were taken simultaneously, even in the case of highly dynamic scenes.

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