Related papers: TinyTracker: Ultra-Fast and Ultra-Low-Power Edge V…
Gaze tracking is increasingly becoming an essential component in Augmented and Virtual Reality. Modern gaze tracking al gorithms are heavyweight; they operate at most 5 Hz on mobile processors despite that near-eye cameras comfortably…
Minutiae extraction, a fundamental stage in fingerprint recognition, is increasingly shifting toward deep learning. However, truly end-to-end methods that eliminate separate preprocessing and postprocessing steps remain scarce. This paper…
Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…
INTPIX4NA is an integration-type silicon-on-insulator pixel detector. This detector has a 14.1 x 8.7 mm^2 sensitive area, 425,984 (832 column x 512 row matrix) pixels and the pixel size is 17 x 17 um^2. This detector was developed for…
After the successful installation and first operation of the new Inner Tracking System (ITS2), which consists of about 10 m$^2$ of monolithic silicon pixel sensors, ALICE is pioneering the usage of bent, wafer-scale pixel sensors for the…
Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance. To achieve satisfactory performance, the methods employ refined…
With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks…
As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…
This dissertation advances the state of the art for AR/VR tracking systems by increasing the tracking frequency by orders of magnitude and proposes an efficient algorithm for the problem of edge-aware optimization. AR/VR is a natural way of…
Transformer-based models are becoming more and more intelligent and are revolutionizing a wide range of human tasks. To support their deployment, AI labs offer inference services that consume hundreds of GWh of energy annually and charge…
Vision Transformers (ViTs) have demonstrated strong capabilities in interpreting complex medical imaging data. However, their significant computational and memory demands pose challenges for deployment in real-time, resource-constrained…
Computing-in-memory (CIM) is renowned in deep learning due to its high energy efficiency resulting from highly parallel computing with minimal data movement. However, current SRAM-based CIM designs suffer from long latency for loading…
A significant limitation of current smartphone-based eye-tracking algorithms is their low accuracy when applied to video-type visual stimuli, as they are typically trained on static images. Also, the increasing demand for real-time…
The use of deep learning models within scientific experimental facilities frequently requires low-latency inference, so that, for example, quality control operations can be performed while data are being collected. Edge computing devices…
Eye-tracking is a vital technology for human-computer interaction, especially in wearable devices such as AR, VR, and XR. The realization of high-speed and high-precision eye-tracking using frame-based image sensors is constrained by their…
Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning…
This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…
We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze…
In this paper, we present Mondrian, an edge system that enables high-performance object detection on high-resolution video streams. Many lightweight models and system optimization techniques have been proposed for resource-constrained…
We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to…