Related papers: Semantic-Discriminative Mixup for Generalizable Se…

Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising approaches to achieve domain generalization (DG) is generating…

The use of supervised learning for Human Activity Recognition (HAR) on mobile devices leads to strong classification performances. Such an approach, however, requires large amounts of labeled data, both for the initial training of the…

Human Activity Recognition (HAR) is a fundamental technology for numerous human - centered intelligent applications. Although deep learning methods have been utilized to accelerate feature extraction, issues such as multimodal data mixing,…

Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling large-scale training data is very expensive and time-consuming,…

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements…

Sensor-based human activity recognition (HAR) mines activity patterns from the time-series sensory data. In realistic scenarios, variations across individuals, devices, environments, and time introduce significant distributional shifts for…

Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…

Cross-dataset Human Activity Recognition (HAR) suffers from limited model generalization, hindering its practical deployment. To address this critical challenge, inspired by the success of DoReMi in Large Language Models (LLMs), we…

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most…

The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data…

Low-resolution infrared-based human activity recognition (HAR) attracted enormous interests due to its low-cost and private. In this paper, a novel semi-supervised crossdomain neural network (SCDNN) based on 8 $\times$ 8 low-resolution…

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Human activity recognition (HAR) from on-body sensors is a core functionality in many AI applications: from personal health, through sports and wellness to Industry 4.0. A key problem holding up progress in wearable sensor-based HAR,…

The ubiquitous availability of smartphones and smartwatches with integrated inertial measurement units (IMUs) enables straightforward capturing of human activities. For specific applications of sensor based human activity recognition (HAR),…

Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies…

The primary objective of human activity recognition (HAR) is to infer ongoing human actions from sensor data, a task that finds broad applications in health monitoring, safety protection, and sports analysis. Despite proliferating research,…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain distributions, with a small number of target labels available, achieving better classification performance than unsupervised domain adaptation (UDA). However,…

Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the scarcity of labeled data limit its real-world generalization. Recent advances in…

Human Activity Recognition (HAR) aims to recognize activities by training models on massive sensor data. In real-world deployment, a crucial aspect of HAR that has been largely overlooked is that the test sets may have different…