Cross-domain Activity Recognition via Substructural Optimal Transport (2021-01-29T00:00:00.000000Z)

TL;DR

This paper proposes substructure-level matching for domain adaptation (SSDA) to better utilize the locality information of activity data for accurate and efficient knowledge transfer and proposes an optimal transport-based implementation, Substructural Optimal Transport (SOT), for cross-domain HAR.

Authors

Jindong Wang

7 papers

Yiqiang Chen

2 papers

Wang Lu

1 papers

Xin Qin

1 papers

TL;DR

Authors

References66 items

Local Domain Adaptation for Cross-Domain Activity Recognition

Deep Visual Domain Adaptation

Vision-based human activity recognition: a survey

Classification of electromyographic hand gesture signals using machine learning techniques

Sensor-based and vision-based human activity recognition: A comprehensive survey

Metric Learning in Optimal Transport for Domain Adaptation

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

Deep Subdomain Adaptation Network for Image Classification

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning

Transfer Learning with Dynamic Distribution Adaptation

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition

A Survey of Unsupervised Deep Domain Adaptation

A hybrid spatio-temporal model for detection and severity rating of Parkinson's disease from gait data

A Survey on Deep Transfer Learning

Autonomous Training of Activity Recognition Algorithms in Mobile Sensors: A Transfer Learning Approach in Context-Invariant Views

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

A novel random forests based class incremental learning method for activity recognition

Unsupervised Domain Adaptation Using Regularized Hyper-Graph Matching

Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

Human Activity Recognition from Body Sensor Data using Deep Learning

A robust human activity recognition system using smartphone sensors and deep learning

Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation

Infrared–ultrasonic sensor fusion for support vector machine–based fall detection

Action recognition based on hierarchical dynamic Bayesian network

Deep Visual Domain Adaptation: A Survey

Stratified Transfer Learning for Cross-domain Activity Recognition

On the Bures–Wasserstein distance between positive definite matrices

Balanced Distribution Adaptation for Transfer Learning

Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture

Deep Learning for Sensor-based Activity Recognition: A Survey

Sensor Fault Classification Based on Support Vector Machine and Statistical Time-Domain Features

Cross-Domain Recognition by Identifying Joint Subspaces of Source Domain and Target Domain

Collegial activity learning between heterogeneous sensors

All-inkjet-printed low-pass filters with adjustable cutoff frequency consisting of resistors, inductors and transistors for sensor applications

Theoretical Analysis of Domain Adaptation with Optimal Transport

Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders

The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition

A Triaxial Accelerometer-Based Human Activity Recognition via EEMD-Based Features and Game-Theory-Based Feature Selection

A comprehensive survey of human action recognition with spatio-temporal interest point (STIP) detector

Return of Frustratingly Easy Domain Adaptation

Optimal Transport for Domain Adaptation

Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units

Transfer Joint Matching for Unsupervised Domain Adaptation

Transfer Feature Learning with Joint Distribution Adaptation

Unsupervised Visual Domain Adaptation Using Subspace Alignment

Transfer learning for activity recognition: a survey

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine

USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors

Introducing a New Benchmarked Dataset for Activity Monitoring

Cross-People Mobile-Phone Based Activity Recognition

A Survey on Transfer Learning

Domain Adaptation via Transfer Component Analysis

Optimal Transport: Old and New

Distance Metric Learning for Large Margin Nearest Neighbor Classification

Estimating the Dimension of a Model

Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

Computational optimal transport: With applications to data science

Real-time human activity recognition from accelerometer data using Convolutional Neural Networks

Label propagation: An unsupervised similarity based method for integrating new sensors in activity recognition systems

Vision Based Human Activity Recognition: A Review

Transition-Aware Human Activity Recognition Using Smartphones

´ edric Villani

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL