Related papers: Low Power Inference for On-Device Visual Recogniti…
CERN's strategic R&D programme on technologies for future experiments recently started investigating the TPSCo 65nm ISC CMOS imaging process for monolithic active pixels sensors for application in high energy physics. In collaboration with…
Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory architecture and narrower gap between CPU and GPU performance…
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high…
Vehicle-to-everything (V2X) communications impose stringent physical-layer integrity requirements, particularly under short-packet transmission and mobility-induced channel variation. This paper studies whether standard-compliant online…
We present the first physical realization of in-pixel signal processing with integrated AI-based data filtering for particle tracking detectors. Building on prior work that demonstrated a physics-motivated edge-AI algorithm suitable for…
High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly…
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough…
Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution…
Mobile traffic prediction is an important enabler for optimizing resource allocation and improving energy efficiency in mobile wireless networks. Building on the advanced contextual understanding and generative capabilities of large…
The ALICE Experiment has replaced its Inner Tracking System with a 7-layer pixel-only tracker made out of more than 24000 monolithic active pixel sensor chips, in order to fulfill the requirements of the physics program of the LHC Run 3.…
The License Plate Recognition (LPR) field has made impressive advances in the last decade due to novel deep learning approaches combined with the increased availability of training data. However, it still has some open issues, especially…
In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image. In particular, we firstly evaluate different low…
Processing-in-memory (PIM) architectures have seen an increase in popularity recently, as the high internal bandwidth available within 3D-stacked memory provides greater incentive to move some computation into the logic layer of the memory.…
As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…
This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This manuscript focuses on the competition set-up, the proposed methods and…
Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement…
Processing-in-memory (PIM) based on emerging devices such as memristors is more vulnerable to noise than traditional memories, due to the physical non-idealities and complex operations in analog domains. To ensure high reliability,…
Night Photography Rendering (NPR) poses a significant challenge due to the extreme contrast between dark and illuminated areas in scenes, stemming from concurrent capture of severely dark regions alongside intense point light sources.…
Light detection and ranging (LiDAR) sensors are becoming available on modern mobile devices and provide a 3D sensing capability. This new capability is beneficial for perceptions in various use cases, but it is challenging for…
Iris pattern recognition has significantly improved the biometric authentication field due to its high stability and uniqueness. Such physical characteristics have played an essential role in security and other related areas. However,…