Related papers: Hyperion: Low-Latency Ultra-HD Video Analytics via…
Slow motion videos are becoming increasingly popular, but capturing high-resolution videos at extremely high frame rates requires professional high-speed cameras. To mitigate this problem, current techniques increase the frame rate of…
Motivated by the proliferation of Internet-of-Thing (IoT) devices and the rapid advances in the field of deep learning, there is a growing interest in pushing deep learning computations, conventionally handled by the cloud, to the edge of…
Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computational requirements, which typically require expensive cloud…
Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Network architectures and achieved state-of-the-art results in various computer vision tasks. Since ViTs are computationally expensive, the models either have to…
We present an advance in wearable technology: a mobile-optimized, real-time, ultra-low-power event camera system that enables natural hand gesture control for smart glasses, dramatically improving user experience. While hand gesture…
Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment,…
In an increasingly visual world, people with blindness and low vision (pBLV) face substantial challenges in navigating their surroundings and interpreting visual information. From our previous work, VIS4ION is a smart wearable that helps…
Current perception models for different tasks usually exist in modular forms on Unmanned Surface Vehicles (USVs), which infer extremely slowly in parallel on edge devices, causing the asynchrony between perception results and USV position,…
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…
Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on dense 3D features, which substantially escalate…
Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for…
Despite the prevailing transition from single-task to multi-task approaches in video anomaly detection, we observe that many adopt sub-optimal frameworks for individual proxy tasks. Motivated by this, we contend that optimizing single-task…
In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera…
Event cameras are innovative neuromorphic sensors that asynchronously capture the scene dynamics. Due to the event-triggering mechanism, such cameras record event streams with much shorter response latency and higher intensity sensitivity…
Visual inspection is the predominant technique for evaluating the condition of civil infrastructure. The recent advances in unmanned aerial vehicles (UAVs) and artificial intelligence have made the visual inspections faster, safer, and more…
Real-time ultrahigh-speed rendering of digital holograms from high-bitrate interferogram streams demands robust parallel computing and efficient data handling with minimal latency. We present Holovibes, a high-performance software engine…
In this paper we propose FastViDAR, a novel framework that takes four fisheye camera inputs and produces a full $360^\circ$ depth map along with per-camera depth, fusion depth, and confidence estimates. Our main contributions are: (1) We…
The role of long- and short-term dynamics towards salient object detection in videos is under-researched. We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model…
Real-time, energy-efficient inference on edge devices is essential for graph classification across a range of applications. Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that encodes input features into…
Multi-sensor frameworks provide opportunities for ensemble learning and sensor fusion to make use of redundancy and supplemental information, helpful in real-world safety applications such as continuous driver state monitoring which…