Beijing Institute of Technology

Beijing Institute of Technology, is a co-educational public university, located in Beijing, China, established in 1940, Yan'an.

Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data

The Artificial Neural Networks (ANNs) have been originally designed to f...
01/05/2019 ∙ by Usman Ahmad, et al. ∙ 30 ∙ share

read it
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer

Nowadays, deep learning techniques are widely used for lane detection, b...
02/04/2020 ∙ by Tong Liu, et al. ∙ 25 ∙ share

read it
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features

With the rapid development of spaceborne imaging techniques, object dete...
01/23/2019 ∙ by Xin Wu, et al. ∙ 24 ∙ share

read it
Assessing the Memory Ability of Recurrent Neural Networks

It is known that Recurrent Neural Networks (RNNs) can remember, in their...
02/18/2020 ∙ by Cheng Zhang, et al. ∙ 22 ∙ share

read it
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

Recently, deep learning based 3D face reconstruction methods have shown ...
03/20/2019 ∙ by Yu Deng, et al. ∙ 20 ∙ share

read it
UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

We propose UniViLM: a Unified Video and Language pre-training Model for ...
02/15/2020 ∙ by Huaishao Luo, et al. ∙ 16 ∙ share

read it
Enhancing Robustness of On-line Learning Models on Highly Noisy Data

Classification algorithms have been widely adopted to detect anomalies f...
03/19/2021 ∙ by Zilong Zhao, et al. ∙ 14 ∙ share

read it
Salient Object Detection in the Deep Learning Era: An In-Depth Survey

As an important problem in computer vision, salient object detection (SO...
04/19/2019 ∙ by Wenguan Wang, et al. ∙ 12 ∙ share

read it
A Novel Deep Neural Network Architecture for Mars Visual Navigation

In this paper, emerging deep learning techniques are leveraged to deal w...
08/25/2018 ∙ by Jiang Zhang, et al. ∙ 8 ∙ share

read it
Multi-Level Attentive Convoluntional Neural Network for Crowd Counting

Recently the crowd counting has received more and more attention. Especi...
05/24/2021 ∙ by Mengxiao Tian, et al. ∙ 8 ∙ share

read it
Domain-adversarial Network Alignment

Network alignment is a critical task to a wide variety of fields. Many e...
08/15/2019 ∙ by Huiting Hong, et al. ∙ 7 ∙ share

read it
EAN: Event Adaptive Network for Enhanced Action Recognition

Efficiently modeling spatial-temporal information in videos is crucial f...
07/22/2021 ∙ by Yuan Tian, et al. ∙ 7 ∙ share

read it
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization

Neural networks with ReLU activations have achieved great empirical succ...
08/14/2018 ∙ by Gang Wang, et al. ∙ 6 ∙ share

read it
Deep Single-View 3D Object Reconstruction with Visual Hull Embedding

3D object reconstruction is a fundamental task of many robotics and AI p...
09/10/2018 ∙ by Hanqing Wang, et al. ∙ 6 ∙ share

read it
P-ODN: Prototype based Open Deep Network for Open Set Recognition

Most of the existing recognition algorithms are proposed for closed set ...
05/06/2019 ∙ by Yu Shu, et al. ∙ 6 ∙ share

read it
SE-Harris and eSUSAN: Asynchronous Event-Based Corner Detection Using Megapixel Resolution CeleX-V Camera

Event cameras are novel neuromorphic vision sensors with ultrahigh tempo...
05/02/2021 ∙ by Jinjian Li, et al. ∙ 5 ∙ share

read it
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

Removing undesirable reflections from a single image captured through a ...
04/01/2019 ∙ by Kaixuan Wei, et al. ∙ 4 ∙ share

read it
Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction

Compressed sensing based magnetic resonance imaging (CS-MRI) provides an...
08/11/2019 ∙ by Wenzhong Zhou, et al. ∙ 4 ∙ share

read it
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation

Acquiring sufficient ground-truth supervision to train deep visual model...
12/09/2020 ∙ by Xueyi Li, et al. ∙ 4 ∙ share

read it
Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Prediction

Midterm stock price prediction is crucial for value investments in the s...
08/03/2019 ∙ by Xinyi Li, et al. ∙ 3 ∙ share

read it
Self-Learning with Rectification Strategy for Human Parsing

In this paper, we solve the sample shortage problem in the human parsing...
04/17/2020 ∙ by Tao Li, et al. ∙ 3 ∙ share

read it
State-aware Anti-drift Robust Correlation Tracking

Correlation filter (CF) based trackers have aroused increasing attention...
06/28/2018 ∙ by Yuqi Han, et al. ∙ 2 ∙ share

read it
Motion-Attentive Transition for Zero-Shot Video Object Segmentation

In this paper, we present a novel Motion-Attentive Transition Network (M...
03/09/2020 ∙ by Tianfei Zhou, et al. ∙ 2 ∙ share

read it
A Unified Object Motion and Affinity Model for Online Multi-Object Tracking

Current popular online multi-object tracking (MOT) solutions apply singl...
03/25/2020 ∙ by Junbo Yin, et al. ∙ 2 ∙ share

read it
Domain Conditioned Adaptation Network

Tremendous research efforts have been made to thrive deep domain adaptat...
05/14/2020 ∙ by Shuang Li, et al. ∙ 2 ∙ share

read it
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

Real-world training data usually exhibits long-tailed distribution, wher...
03/23/2021 ∙ by Shuang Li, et al. ∙ 2 ∙ share

read it
The Disruptions of 5G on Data-driven Technologies and Applications

With 5G on the verge of being adopted as the next mobile network, there ...
09/06/2019 ∙ by Dumitrel Loghin, et al. ∙ 1 ∙ share

read it
SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification

Person re-identification via 3D skeletons is an emerging topic with grea...
07/05/2021 ∙ by Haocong Rao, et al. ∙ 1 ∙ share

read it
Pulsar Candidate Identification with Artificial Intelligence Techniques

Discovering pulsars is a significant and meaningful research topic in th...
11/27/2017 ∙ by Ping Guo, et al. ∙ 0 ∙ share

read it
Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

In this paper, we propose a pose grammar to tackle the problem of 3D hum...
10/17/2017 ∙ by Haoshu Fang, et al. ∙ 0 ∙ share

read it
Deep Cropping via Attention Box Prediction and Aesthetics Assessment

We model the photo cropping problem as a cascade of attention box regres...
10/22/2017 ∙ by Wenguan Wang, et al. ∙ 0 ∙ share

read it
Novel Evaluation Metrics for Seam Carving based Image Retargeting

Image retargeting effectively resizes images by preserving the recogniza...
09/22/2017 ∙ by Tam V. Nguyen, et al. ∙ 0 ∙ share

read it
Solving Almost all Systems of Random Quadratic Equations

This paper deals with finding an n-dimensional solution x to a system of...
05/29/2017 ∙ by Gang Wang, et al. ∙ 0 ∙ share

read it
Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection

Facial recognition and verification is a widely used biometric technolog...
07/10/2017 ∙ by Changyong Yu, et al. ∙ 0 ∙ share

read it
Quadruplet Network with One-Shot Learning for Visual Tracking

As a discriminative method of one-shot learning, Siamese deep network al...
05/19/2017 ∙ by Xingping Dong, et al. ∙ 0 ∙ share

read it
Deep Visual Attention Prediction

Deep Convolutional Neural Networks (CNNs) have made substantial improvem...
05/07/2017 ∙ by Wenguan Wang, et al. ∙ 0 ∙ share

read it
Supervised Deep Hashing for Hierarchical Labeled Data

Recently, hashing methods have been widely used in large-scale image ret...
04/07/2017 ∙ by Dan Wang, et al. ∙ 0 ∙ share

read it
Dual Teaching: A Practical Semi-supervised Wrapper Method

Semi-supervised wrapper methods are concerned with building effective su...
11/12/2016 ∙ by Fuqaing Liu, et al. ∙ 0 ∙ share

read it
Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow

A novel approach termed stochastic truncated amplitude flow (STAF) is de...
10/29/2016 ∙ by Gang Wang, et al. ∙ 0 ∙ share

read it
Selective Video Object Cutout

Conventional video segmentation approaches rely heavily on appearance mo...
02/28/2017 ∙ by Wenguan Wang, et al. ∙ 0 ∙ share

read it
Super-Trajectory for Video Segmentation

We introduce a novel semi-supervised video segmentation approach based o...
02/28/2017 ∙ by Wenguan Wang, et al. ∙ 0 ∙ share

read it
Video Salient Object Detection via Fully Convolutional Networks

This paper proposes a deep learning model to efficiently detect salient ...
02/02/2017 ∙ by Wenguan Wang, et al. ∙ 0 ∙ share

read it
Statistical Pattern Recognition for Driving Styles Based on Bayesian Probability and Kernel Density Estimation

Driving styles have a great influence on vehicle fuel economy, active sa...
06/03/2016 ∙ by Wenshuo Wang, et al. ∙ 0 ∙ share

read it
A Rapid Pattern-Recognition Method for Driving Types Using Clustering-Based Support Vector Machines

A rapid pattern-recognition approach to characterize driver's curve-nego...
05/22/2016 ∙ by Wenshuo Wang, et al. ∙ 0 ∙ share

read it
Efficient phase retrieval based on dark fringe recognition with an ability of bypassing invalid fringes

This paper discusses the noisy phase retrieval problem: recovering a com...
12/14/2016 ∙ by Wen-Kai Yu, et al. ∙ 0 ∙ share

read it
Joint Network based Attention for Action Recognition

By extracting spatial and temporal characteristics in one network, the t...
11/16/2016 ∙ by Yemin Shi, et al. ∙ 0 ∙ share

read it
Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering

Clustering is among the most fundamental tasks in computer vision and ma...
11/16/2016 ∙ by Zhuxi Jiang, et al. ∙ 0 ∙ share

read it
Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN

Learning the spatial-temporal representation of motion information is cr...
09/10/2016 ∙ by Yemin Shi, et al. ∙ 0 ∙ share

read it
Recognizing Car Fluents from Video

Physical fluents, a term originally used by Newton [40], refers to time-...
03/26/2016 ∙ by Bo Li, et al. ∙ 0 ∙ share

read it
Temporal Dynamic Appearance Modeling for Online Multi-Person Tracking

Robust online multi-person tracking requires the correct associations of...
10/10/2015 ∙ by Min Yang, et al. ∙ 0 ∙ share

read it

Beijing Institute of Technology

Featured Researchers