Related papers: Fullie and Wiselie: A Dual-Stream Recurrent Convol…
In many machine learning tasks, input features with varying degrees of predictive capability are acquired at varying costs. In order to optimize the performance-cost trade-off, one would select features to observe a priori. However, given…
Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Applying HAR to wearable sensors can provide new insights by enriching the feature set in health studies, and enhance the personalisation and…
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…
Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that…
Recent years have witnessed the rapid development of human activity recognition (HAR) based on wearable sensor data. One can find many practical applications in this area, especially in the field of health care. Many machine learning…
We consider human activity recognition (HAR) from wearable sensor data in manual-work processes, like warehouse order-picking. Such structured domains can often be partitioned into distinct process steps, e.g., packaging or transporting.…
Human Activity Recognition (HAR) research has gained significant momentum due to recent technological advancements, artificial intelligence algorithms, the need for smart cities, and socioeconomic transformation. However, existing computer…
Human Activity Recognition (HAR) is one of the essential building blocks of so many applications like security, monitoring, the internet of things and human-robot interaction. The research community has developed various methodologies to…
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…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse…
Accurate and robust object detection is critical for autonomous driving. Image-based detectors face difficulties caused by low visibility in adverse weather conditions. Thus, radar-camera fusion is of particular interest but presents…
Action detection and recognition tasks have been the target of much focus in the computer vision community due to their many applications, namely, security, robotics and recommendation systems. Recently, datasets like AVA, provide…
Human activity recognition (HAR) is a crucial area of research that involves understanding human movements using computer and machine vision technology. Deep learning has emerged as a powerful tool for this task, with models such as…
Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…
This paper presents a novel approach for automatic recognition of human activities for video surveillance applications. We propose to represent an activity by a combination of category components, and demonstrate that this approach offers…
Driver Action Recognition (DAR) is crucial in vehicle cabin monitoring systems. In real-world applications, it is common for vehicle cabins to be equipped with cameras featuring different modalities. However, multi-modality fusion…
To fluently collaborate with people, robots need the ability to recognize human activities accurately. Although modern robots are equipped with various sensors, robust human activity recognition (HAR) still remains a challenging task for…
Radar-based Human Activity Recognition (HAR) is an attractive alternative to wearables and cameras because it preserves privacy, and is contactless and robust to occlusions. However, dominant Convolutional Neural Network (CNN)- and…
Random feature (RF) method is a powerful kernel approximation technique, but is typically equipped with fixed activation functions, limiting its adaptability across diverse tasks. To overcome this limitation, we introduce the Random Feature…