Related papers: TRACE: Temporal Reasoning over Context and Evidenc…
Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand dataset-specific training, large labeled corpora, and significant…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Extracting temporal relations among events from unstructured text has extensive applications, such as temporal reasoning and question answering. While it is difficult, recent development of Neural-symbolic methods has shown promising…
Sensory inference under conditions of uncertainty is a major problem in both machine learning and computational neuroscience. An important but poorly understood aspect of sensory processing is the role of active sensing. Here, we present a…
Sensory inference under conditions of uncertainty is a major problem in both machine learning and computational neuroscience. An important but poorly understood aspect of sensory processing is the role of active sensing. Here, we present a…
Smart homes equipped with ambient sensors offer a transformative approach to continuous health monitoring and assisted living. Traditional research in this domain primarily focuses on Human Activity Recognition (HAR), which relies on…
Despite the widespread integration of ambient light sensors (ALS) in smart devices commonly used for screen brightness adaptation, their application in human activity recognition (HAR), primarily through body-worn ALS, is largely…
We relate our previous as well as ongoing research in the domain of smart homes to the concept of HabiTech. HabiTech can benefit from existing approaches and findings in a broader context of whole buildings or communities within. Along with…
Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing. Most recent research in the field adopts supervised deep learning paradigms to automate…
Mobile robots are often deployed over long durations in diverse open, dynamic scenes, including indoor setting such as warehouses and manufacturing facilities, and outdoor settings such as agricultural and roadway operations. A core…
The paper studies sequential reasoning over graph-structured data, which stands as a fundamental task in various trending fields like automated math problem solving and neural graph algorithm learning, attracting a lot of research interest.…
Directional cues are crucial for environmental interaction. Conventional methods rely on symbolic visual or auditory reminders that require semantic interpretation, a process that proves challenging in demanding dual-tasking scenarios. We…
The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulate this problem as a sequence-to-sequence task, in which a…
The concern over global urbanization trend imposes smart-city as enabling information and communication technology (ICT) to improve urban governance. However, the light trance on better living space is stimulated by socioeconomic impact of…
3D action recognition - analysis of human actions based on 3D skeleton data - becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based…
Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs),…
Human Activity Recognition (HAR) plays a critical role in a wide range of real-world applications, and it is traditionally achieved via wearable sensing. Recently, to avoid the burden and discomfort caused by wearable devices, device-free…
Transformer models have demonstrated exceptional performance across a wide range of applications. Though forming the foundation of Transformer models, the dot-product attention does not scale well to long-context data since its time…
Deep Learning models are a standard solution for sensor-based Human Activity Recognition (HAR), but their deployment is often limited by labeled data scarcity and models' opacity. Neuro-Symbolic AI (NeSy) provides an interesting research…
Person Search is a relevant task that aims to jointly solve Person Detection and Person Re-identification(re-ID). Though most previous methods focus on learning robust individual features for retrieval, it's still hard to distinguish…