Related papers: Initial Findings on Sensor based Open Vocabulary A…
Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-vocabulary detector…
Given the growing trend of continual learning techniques for deep neural networks focusing on the domain of computer vision, there is a need to identify which of these generalizes well to other tasks such as human activity recognition…
Many deep architectures and self-supervised pre-training techniques have been proposed for human activity recognition (HAR) from wearable multimodal sensors. Scaling laws have the potential to help move towards more principled design by…
Human activity recognition (HAR) is a classification task that aims to classify human activities or predict human behavior by means of features extracted from sensors data. Typical HAR systems use wearable sensors and/or handheld and mobile…
In smart healthcare, Human Activity Recognition (HAR) is considered to be an efficient model in pervasive computation from sensor readings. The Ambient Assisted Living (AAL) in the home or community helps the people in providing independent…
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained…
Current human activity recognition (HAR) techniques regard activity labels as integer class IDs without explicitly modeling the semantics of class labels. We observe that different activity names often have shared structures. For example,…
Supervised Deep Learning (DL) models are currently the leading approach for sensor-based Human Activity Recognition (HAR) on wearable and mobile devices. However, training them requires large amounts of labeled data whose collection is…
Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for…
Most approaches that model time-series data in human activity recognition based on body-worn sensing (HAR) use a fixed size temporal context to represent different activities. This might, however, not be apt for sets of activities with…
Due to the increasing number of mobile robots including domestic robots for cleaning and maintenance in developed countries, human activity recognition is inevitable for congruent human-robot interaction. Needless to say that this is indeed…
Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action…
Human Activity Recognition (HAR) is a crucial technology for many applications such as smart homes, surveillance, human assistance and health care. This technology utilises pattern recognition and can contribute to the development of…
Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector…
To address the limitations of existing open-vocabulary object recognition methods, specifically high system complexity, substantial training costs, and limited generalization, this paper proposes a novel Open-Vocabulary Object Recognition…
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,…
We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are learned by training a…
Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often…
Human activity recognition (HAR) in Internet of Things (IoT) environments must cope with heterogeneous sensor settings that vary across datasets, devices, body locations, sensing modalities, and channel compositions. This heterogeneity…
The lack of standardization across Wearable Human Activity Recognition (WHAR) datasets limits reproducibility, comparability, and research efficiency. We introduce WHAR datasets, an open-source library designed to simplify WHAR data…