Related papers: Perceptual Requirements for Low-Latency Head-Mount…
5G communication brings substantial improvements in the quality of service provided to various applications by achieving higher throughput and lower latency. However, interactive multimedia applications (e.g., ultra high definition video…
End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely…
Assistive devices, such as exoskeletons and prostheses, have revolutionized the field of rehabilitation and mobility assistance. Efficiently detecting transitions between different activities, such as walking, stair ascending and…
Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, intermittent, and frequently co-occurring expressions hinder…
World models aim to understand, remember, and predict dynamic visual environments, yet a unified benchmark for evaluating their fundamental abilities remains lacking. To address this gap, we introduce MIND, the first open-domain closed-loop…
In robotic systems, perception latency is a term that refers to the computing time measured from the data acquisition to the moment in which perception output is ready to be used to compute control commands. There is a compromise between…
End-to-end autonomous driving faces persistent challenges in both generating diverse, rule-compliant trajectories and robustly selecting the optimal path from these options via learned, multi-faceted evaluation. To address these challenges,…
Human pose estimation (HPE) is a classical task in computer vision that focuses on representing the orientation of a person by identifying the positions of their joints. We design a lighterversion of the stacked hourglass network with…
Monocular egocentric 3D human motion capture remains a significant challenge, particularly under conditions of low lighting and fast movements, which are common in head-mounted device applications. Existing methods that rely on RGB cameras…
We aim to make learned point cloud compression deployable for low-latency streaming on mobile systems. While learned point cloud compression has shown strong coding efficiency, practical deployment on mobile platforms remains challenging…
In this paper, we introduce HEADS-UP, the first egocentric dataset collected from head-mounted cameras, designed specifically for trajectory prediction in blind assistance systems. With the growing population of blind and visually impaired…
Vision based human pose estimation is an non-invasive technology for Human-Computer Interaction (HCI). Direct use of the hand as an input device provides an attractive interaction method, with no need for specialized sensing equipment, such…
For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on…
Target tracking is a popular problem with many potential applications. There has been a lot of effort on improving the quality of the detection of targets using cameras through different techniques. In general, with higher computational…
Modern Edge-to-Cloud (E2C) systems require fine-grained observability to ensure adaptive behavior and compliance with performance objectives across heterogeneous and dynamic environments. This work introduces an application-level…
Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and…
The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN-based methods can achieve good…
Edge Machine Learning (Edge ML), which shifts computational intelligence from cloud-based systems to edge devices, is attracting significant interest due to its evident benefits including reduced latency, enhanced data privacy, and…
Responsiveness in large language model (LLM) applications is widely assumed to be critical, yet the impact of latency on user behavior and perception of output quality has not been systematically explored. We report a controlled experiment…
For realizing safe autonomous driving, the end-to-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays,…