Harbin Institute of Technology

∙ Haerbin Shi , China ∙ 0 followers

The Harbin Institute of Technology is a research university and a member of China's elite C9 League.

Learning an Adaptive Model for Extreme Low-light Raw Image Processing

Low-light images suffer from severe noise and low illumination. Current ...
04/22/2020 ∙ by Qingxu Fu, et al. ∙ 33 ∙ share

read it
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

This paper reviews the NTIRE 2020 challenge on real image denoising with...
05/08/2020 ∙ by Abdelrahman Abdelhamed, et al. ∙ 25 ∙ share

read it
Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

In many practical transfer learning scenarios, the feature distribution ...
03/25/2019 ∙ by Lei Zhang, et al. ∙ 22 ∙ share

read it
Universal, transferable and targeted adversarial attacks

Deep Neural Network has been found vulnerable in many previous works. A ...
08/29/2019 ∙ by Junde Wu, et al. ∙ 22 ∙ share

read it
Optimized CNN for PolSAR Image Classification via Differentiable Neural Architecture Search

Convolutional neural networks (CNNs) realize the automation of feature e...
11/16/2019 ∙ by Hongwei Dong, et al. ∙ 17 ∙ share

read it
Pyramid Feature Selective Network for Saliency detection

Saliency detection is one of the basic challenges in computer vision. Ho...
03/01/2019 ∙ by Ting Zhao, et al. ∙ 14 ∙ share

read it
Filter Grafting for Deep Neural Networks

This paper proposes a new learning paradigm called filter grafting, whic...
01/15/2020 ∙ by Fanxu Meng, et al. ∙ 14 ∙ share

read it
Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints

Breast cancer is one of the most serious disease affects women's health....
09/14/2019 ∙ by Kuan Huang, et al. ∙ 13 ∙ share

read it
Learning deep neural networks in blind deblurring framework

Recently, end-to-end learning methods based on deep neural network (DNN)...
03/07/2019 ∙ by Junde Wu, et al. ∙ 12 ∙ share

read it
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Hyperspectral imaging can help better understand the characteristics of ...
01/10/2019 ∙ by Qi Xie, et al. ∙ 10 ∙ share

read it
TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks

Lightweight or mobile neural networks used for real-time computer vision...
03/22/2020 ∙ by Xinyu Liu, et al. ∙ 9 ∙ share

read it
Hyperspectral Image Classification in the Presence of Noisy Labels

Label information plays an important role in supervised hyperspectral im...
09/12/2018 ∙ by Junjun Jiang, et al. ∙ 8 ∙ share

read it
Learning Symmetry Consistent Deep CNNs for Face Completion

Deep convolutional networks (CNNs) have achieved great success in face c...
12/19/2018 ∙ by Xiaoming Li, et al. ∙ 8 ∙ share

read it
Mutual Information Gradient Estimation for Representation Learning

Mutual Information (MI) plays an important role in representation learni...
05/03/2020 ∙ by Liangjian Wen, et al. ∙ 6 ∙ share

read it
Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking

Existing deep Thermal InfraRed (TIR) trackers only use semantic features...
06/09/2019 ∙ by Qiao Liu, et al. ∙ 5 ∙ share

read it
Assembly of randomly placed parts realized by using only one robot arm with a general parallel-jaw gripper

In industry assembly lines, parts feeding machines are widely employed a...
09/19/2019 ∙ by Jie Zhao, et al. ∙ 5 ∙ share

read it
Meta3D: Single-View 3D Object Reconstruction from Shape Priors in Memory

3D shape reconstruction from a single-view RGB image is an ill-posed pro...
03/08/2020 ∙ by Shuo Yang, et al. ∙ 5 ∙ share

read it
TCDesc: Learning Topology Consistent Descriptors

Triplet loss is widely used for learning local descriptors from image pa...
06/05/2020 ∙ by Honghu Pan, et al. ∙ 5 ∙ share

read it
Cross-Scale Internal Graph Neural Network for Image Super-Resolution

Non-local self-similarity in natural images has been well studied as an ...
06/30/2020 ∙ by Shangchen Zhou, et al. ∙ 5 ∙ share

read it
Neural Melody Composition from Lyrics

In this paper, we study a novel task that learns to compose music from n...
09/12/2018 ∙ by Hangbo Bao, et al. ∙ 4 ∙ share

read it
Siamese Box Adaptive Network for Visual Tracking

Most of the existing trackers usually rely on either a multi-scale searc...
03/15/2020 ∙ by Zedu Chen, et al. ∙ 4 ∙ share

read it
Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery

Recently, single gray/RGB image super-resolution reconstruction task has...
05/18/2020 ∙ by Junjun Jiang, et al. ∙ 4 ∙ share

read it
Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction

A learning-based 3D reconstruction method for long-span bridges is propo...
07/08/2019 ∙ by Fangqiao Hu, et al. ∙ 3 ∙ share

read it
Rapid Whole Slide Imaging via Learning-based Two-shot Virtual Autofocusing

Whole slide imaging (WSI) is an emerging technology for digital patholog...
03/14/2020 ∙ by Qiang Li, et al. ∙ 3 ∙ share

read it
Shift-Net: Image Inpainting via Deep Feature Rearrangement

Deep convolutional networks (CNNs) have exhibited their potential in ima...
01/29/2018 ∙ by Zhaoyi Yan, et al. ∙ 2 ∙ share

read it
Towards Explainable NLP: A Generative Explanation Framework for Text Classification

Building explainable systems is a critical problem in the field of Natur...
11/01/2018 ∙ by Hui Liu, et al. ∙ 1 ∙ share

read it
Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification

Convolutional neural networks (CNNs) have shown good performance in pola...
11/16/2019 ∙ by Hongwei Dong, et al. ∙ 1 ∙ share

read it
Attention-over-Attention Neural Networks for Reading Comprehension

Cloze-style queries are representative problems in reading comprehension...
07/15/2016 ∙ by Yiming Cui, et al. ∙ 0 ∙ share

read it
Particle Filter Re-detection for Visual Tracking via Correlation Filters

Most of the correlation filter based tracking algorithms can achieve goo...
11/28/2017 ∙ by Di Yuan, et al. ∙ 0 ∙ share

read it
Hierarchical Siamese Network for Thermal Infrared Object Tracking

Most thermal infrared (TIR) tracking methods are discriminative, which t...
11/27/2017 ∙ by Qiao Liu, et al. ∙ 0 ∙ share

read it
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation

The aspect ratio variation frequently appears in visual tracking and has...
10/05/2017 ∙ by Yingjie Yao, et al. ∙ 0 ∙ share

read it
Coalition formation for Multi-agent Pursuit based on Neural Network and AGRMF Model

An approach for coalition formation of multi-agent pursuit based on neur...
07/17/2017 ∙ by Zhaoyi Pei, et al. ∙ 0 ∙ share

read it
Consensus Attention-based Neural Networks for Chinese Reading Comprehension

Reading comprehension has embraced a booming in recent NLP research. Sev...
07/08/2016 ∙ by Yiming Cui, et al. ∙ 0 ∙ share

read it
Towards well-specified semi-supervised model-based classifiers via structural adaptation

Semi-supervised learning plays an important role in large-scale machine ...
05/01/2017 ∙ by Zhaocai Sun, et al. ∙ 0 ∙ share

read it
Automatic Dataset Augmentation

Large scale image dataset and deep convolutional neural network (DCNN) a...
08/28/2017 ∙ by Yalong Bai, et al. ∙ 0 ∙ share

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

Deep learning, e.g., convolutional neural networks (CNNs), has achieved ...
08/02/2017 ∙ by Feng Jiang, et al. ∙ 0 ∙ share

read it
Learning Deep CNN Denoiser Prior for Image Restoration

Model-based optimization methods and discriminative learning methods hav...
04/11/2017 ∙ by Kai Zhang, et al. ∙ 0 ∙ share

read it
Learning Convolutional Networks for Content-weighted Image Compression

Lossy image compression is generally formulated as a joint rate-distorti...
03/30/2017 ∙ by Mu Li, et al. ∙ 0 ∙ share

read it
Is Second-order Information Helpful for Large-scale Visual Recognition?

By stacking layers of convolution and nonlinearity, convolutional networ...
03/23/2017 ∙ by Peihua Li, et al. ∙ 0 ∙ share

read it
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Recent years have witnessed the unprecedented success of deep convolutio...
12/17/2017 ∙ by Kai Zhang, et al. ∙ 0 ∙ share

read it
Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs

This paper proposes a novel saliency detection method by combining regio...
08/18/2016 ∙ by Youbao Tang, et al. ∙ 0 ∙ share

read it
Random Walk Graph Laplacian based Smoothness Prior for Soft Decoding of JPEG Images

Given the prevalence of JPEG compressed images, optimizing image reconst...
07/07/2016 ∙ by Xianming Liu, et al. ∙ 0 ∙ share

read it
Feature selection with test cost constraint

Feature selection is an important preprocessing step in machine learning...
09/25/2012 ∙ by Fan Min, et al. ∙ 0 ∙ share

read it
Towards Effective Codebookless Model for Image Classification

The bag-of-features (BoF) model for image classification has been thorou...
07/09/2015 ∙ by Qilong Wang, et al. ∙ 0 ∙ share

read it
Visualizing and Comparing Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have achieved comparable error rate...
12/20/2014 ∙ by Wei Yu, et al. ∙ 0 ∙ share

read it
Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data

Image retrieval refers to finding relevant images from an image database...
12/17/2013 ∙ by Yalong Bai, et al. ∙ 0 ∙ share

read it
Guarantees of Augmented Trace Norm Models in Tensor Recovery

This paper studies the recovery guarantees of the models of minimizing X...
07/23/2012 ∙ by Ziqiang Shi, et al. ∙ 0 ∙ share

read it
Dataset for the First Evaluation on Chinese Machine Reading Comprehension

Machine Reading Comprehension (MRC) has become enormously popular recent...
09/25/2017 ∙ by Yiming Cui, et al. ∙ 0 ∙ share

read it
A Question Answering Approach to Emotion Cause Extraction

Emotion cause extraction aims to identify the reasons behind a certain e...
08/18/2017 ∙ by Lin Gui, et al. ∙ 0 ∙ share

read it
Selective Encoding for Abstractive Sentence Summarization

We propose a selective encoding model to extend the sequence-to-sequence...
04/24/2017 ∙ by Qingyu Zhou, et al. ∙ 0 ∙ share

read it

Harbin Institute of Technology

Featured Researchers