37 citations · 110 across the 12 of their papers we have counts for
12 papers
ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition
Shuai Shao, Yu Guan, Bing Zhai +2
Human activity recognition (HAR) is one of the core research themes in ubiquitous and wearable computing. With the shift to deep learning (DL) based analysis approaches, it has bec…
Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Jifan Zhang, Shuai Shao, Saurabh Verma +1
Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep ne…
Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognition
Shuai Shao, Yu Guan, Xin Guan +2
Human Activity Recognition (HAR) is one of the core research areas in mobile and wearable computing. With the application of deep learning (DL) techniques such as CNN, recognizing…
GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
Rui Xu, Lei Xing, Shuai Shao +4
Few-shot learning (FSL), purposing to resolve the problem of data-scarce, has attracted considerable attention in recent years. A popular FSL framework contains two phases: (i) the…
SSDL: Self-Supervised Dictionary Learning
Shuai Shao, Lei Xing, Wei Yu +3
The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the labe…
MDFM: Multi-Decision Fusing Model for Few-Shot Learning
Shuai Shao, Lei Xing, Rui Xu +3
In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i…
CIM: Class-Irrelevant Mapping for Few-Shot Classification
Shuai Shao, Lei Xing, Yixin Chen +3
Few-shot classification (FSC) is one of the most concerned hot issues in recent years. The general setting consists of two phases: (1) Pre-train a feature extraction model (FEM) wi…
MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
Shuai Shao, Lei Xing, Yan Wang +4
Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based…
DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization
Shuai Shao, Mengke Wang, Rui Xu +2
For classification tasks, dictionary learning based methods have attracted lots of attention in recent years. One popular way to achieve this purpose is to introduce label informat…
SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning
Shuai Shao, Rui Xu, Yan-Jiang Wang +2
In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propaga…
Label Embedded Dictionary Learning for Image Classification
Shuai Shao, Yan-Jiang Wang, Bao-Di Liu +2
Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error,…
Class specific or shared? A cascaded dictionary learning framework for image classification
Yan-Jiang Wang, Shuai Shao, Rui Xu +2
Dictionary learning methods can be split into: i) class specific dictionary learning ii) class shared dictionary learning. The difference between the two categories is how to use d…