1.1k citations · 2.2k across the 32 of their papers we have counts for
32 papers
Robust Depth Completion with Uncertainty-Driven Loss Functions
Yufan Zhu, Weisheng Dong, Leida Li +3
Recovering a dense depth image from sparse LiDAR scans is a challenging task. Despite the popularity of color-guided methods for sparse-to-dense depth completion, they treated pixe…
Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks
Chenxin Xu, Rong Xia, Yong Xiao +3
With the fast growing demand on new services and applications as well as the increasing awareness of data protection, traditional centralized traffic classification approaches are…
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
Pengfei Wang, Chengquan Zhang, Fei Qi +7
The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based metho…
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
Tao Huang, Weisheng Dong, Xin Yuan +2
In coded aperture snapshot spectral imaging (CASSI) system, the real-world hyperspectral image (HSI) can be reconstructed from the captured compressive image in a snapshot. Model-b…
A new communication paradigm: from bit accuracy to semantic fidelity
Guangming Shi, Dahua Gao, Xiaodan Song +5
Wireless communication has achieved great success in the past several decades. The challenge is of improving bandwidth with limited spectrum and power consumption, which however ha…
Optical Flow Estimation via Motion Feature Recovery
Yang Jiao, Guangming Shi, Trac D. Tran
Optical flow estimation with occlusion or large displacement is a problematic challenge due to the lost of corresponding pixels between consecutive frames. In this paper, we discov…
Temporal Graph Modeling for Skeleton-based Action Recognition
Jianan Li, Xuemei Xie, Zhifu Zhao +3
Graph Convolutional Networks (GCNs), which model skeleton data as graphs, have obtained remarkable performance for skeleton-based action recognition. Particularly, the temporal dyn…
From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problems
Guangming Shi, Yong Xiao, Yingyu Li +1
Existing communication systems are mainly built based on Shannon's information theory which deliberately ignores the semantic aspects of communication. The recent iteration of wire…
Optimizing Resource-Efficiency for Federated Edge Intelligence in IoT Networks
Yong Xiao, Yingyu Li, Guangming Shi +1
This paper studies an edge intelligence-based IoT network in which a set of edge servers learn a shared model using federated learning (FL) based on the datasets uploaded from a mu…
2D+3D Facial Expression Recognition via Discriminative Dynamic Range Enhancement and Multi-Scale Learning
Yang Jiao, Yi Niu, Trac D. Tran +1
In 2D+3D facial expression recognition (FER), existing methods generate multi-view geometry maps to enhance the depth feature representation. However, this may introduce false esti…
EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation
Yang Jiao, Trac D. Tran, Guangming Shi
This paper addresses the challenging unsupervised scene flow estimation problem by jointly learning four low-level vision sub-tasks: optical flow , stereo-depth $\textb…
Towards Self-learning Edge Intelligence in 6G
Yong Xiao, Guangming Shi, Yingyu Li +2
Edge intelligence, also called edge-native artificial intelligence (AI), is an emerging technological framework focusing on seamless integration of AI, communication networks, and…
A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition
Yang Li, Boxun Fu, Fu Li +2
The existed methods for electroencephalograph (EEG) emotion recognition always train the models based on all the EEG samples indistinguishably. However, some of the source (trainin…
Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
Qian Ning, Weisheng Dong, Guangming Shi +2
Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR). However, existing state-of-the-art SISR techniques are designed like…
Towards Ubiquitous AI in 6G with Federated Learning
Yong Xiao, Guangming Shi, Marwan Krunz
With 5G cellular systems being actively deployed worldwide, the research community has started to explore novel technological advances for the subsequent generation, i.e., 6G. It i…
MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment
Hancheng Zhu, Leida Li, Jinjian Wu +2
Recently, increasing interest has been drawn in exploiting deep convolutional neural networks (DCNNs) for no-reference image quality assessment (NR-IQA). Despite of the notable suc…
A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
Pengfei Wang, Chengquan Zhang, Fei Qi +6
Detecting scene text of arbitrary shapes has been a challenging task over the past years. In this paper, we propose a novel segmentation-based text detector, namely SAST, which emp…
DarwinML: A Graph-based Evolutionary Algorithm for Automated Machine Learning
Fei Qi, Zhaohui Xia, Gaoyang Tang +6
As an emerging field, Automated Machine Learning (AutoML) aims to reduce or eliminate manual operations that require expertise in machine learning. In this paper, a graph-based arc…
Knowledge-guided Semantic Computing Network
Guangming Shi, Zhongqiang Zhang, Dahua Gao +4
It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. Howeve…
Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding
Fangfang Wu, Weisheng Dong, Guangming Shi +1
State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to ex…
The Shape of Sight: A Homological Framework for Unifying Visual Perception
Xin Li
Visual perception, the brain's construction of a stable world from sensory data, faces several long-standing, fundamental challenges. While often studied separately, these problems…
Full Image Recover for Block-Based Compressive Sensing
Xuemei Xie, Chenye Wang, Jiang Du +1
Recent years, compressive sensing (CS) has improved greatly for the application of deep learning technology. For convenience, the input image is usually measured and reconstructed…
Perceptual Compressive Sensing
Jiang Du, Xuemei Xie, Chenye Wang +1
Compressive sensing (CS) works to acquire measurements at sub-Nyquist rate and recover the scene images. Existing CS methods always recover the scene images in pixel level. This ca…
ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
Xiaotong Lu, Weisheng Dong, Peiyao Wang +2
Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimen…