中文
相关论文

相关论文: Investigation of event-based memory surfaces for h…

200 篇论文

Emerging event cameras acquire visual information by detecting time domain brightness changes asynchronously at the pixel level and, unlike conventional cameras, are able to provide high temporal resolution, very high dynamic range, low…

多媒体 · 计算机科学 2024-11-06 Ahmadreza Sezavar , Catarina Brites , Joao Ascenso

Mobile and embedded applications require neural networks-based pattern recognition systems to perform well under a tight computational budget. In contrast to commonly used synchronous, frame-based vision systems and CNNs, asynchronous,…

神经与进化计算 · 计算机科学 2019-06-24 Bodo Rückauer , Nicolas Känzig , Shih-Chii Liu , Tobi Delbruck , Yulia Sandamirskaya

Object detection plays a critical role in autonomous driving, where accurately and efficiently detecting objects in fast-moving scenes is crucial. Traditional frame-based cameras face challenges in balancing latency and bandwidth,…

计算机视觉与模式识别 · 计算机科学 2024-05-08 Bingquan Zhou , Jie Jiang

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in…

计算机视觉与模式识别 · 计算机科学 2023-03-23 Saizhe Ding , Jinze Chen , Yang Wang , Yu Kang , Weiguo Song , Jie Cheng , Yang Cao

Automatic event detection from time series signals has wide applications, such as abnormal event detection in video surveillance and event detection in geophysical data. Traditional detection methods detect events primarily by the use of…

机器学习 · 计算机科学 2018-09-26 Yue Wu , Youzuo Lin , Zheng Zhou , David Chas Bolton , Ji Liu , Paul Johnson

Deep learning with a convolutional neural network (CNN) has been proved to be very effective in feature extraction and representation of images. For image classification problems, this work aim at finding which classifier is more…

机器学习 · 计算机科学 2015-06-09 Lei Zhang , David Zhang

Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional cameras: high temporal resolution, high dynamic range, and…

计算机视觉与模式识别 · 计算机科学 2019-04-18 Henri Rebecq , René Ranftl , Vladlen Koltun , Davide Scaramuzza

Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as "events". They have appealing advantages over frame-based cameras for computer vision, including high temporal resolution,…

计算机视觉与模式识别 · 计算机科学 2019-08-21 Daniel Gehrig , Antonio Loquercio , Konstantinos G. Derpanis , Davide Scaramuzza

Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In this paper, we propose a novel approach for reconstructing such deformations using measurements from event-based…

计算机视觉与模式识别 · 计算机科学 2022-11-15 Yuxuan Xue , Haolong Li , Stefan Leutenegger , Jörg Stückler

Spatiotemporal information is at the core of diverse sensory processing and computational tasks. Feed-forward spiking neural networks can be used to solve these tasks while offering potential benefits in terms of energy efficiency by…

机器学习 · 计算机科学 2026-03-11 Jann Krausse , Zhe Su , Kyrus Mama , Maryada , Klaus Knobloch , Giacomo Indiveri , Jürgen Becker

With the success of deep learning, object recognition systems that can be deployed for real-world applications are becoming commonplace. However, inference that needs to largely take place on the `edge' (not processed on servers), is a…

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with…

计算机视觉与模式识别 · 计算机科学 2020-01-16 Marco Monforte , Ander Arriandiaga , Arren Glover , Chiara Bartolozzi

Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high time…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Zhe Jiang , Yu Zhang , Dongqing Zou , Jimmy Ren , Jiancheng Lv , Yebin Liu

Knowledge graphs used for retrieval treat all facts as equally current. Existing temporal approaches apply uniform decay, using a single forgetting curve regardless of knowledge type. We show this is fundamentally misspecified: different…

信息检索 · 计算机科学 2026-05-01 Mandar Karhade

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance. However, existing popular solutions usually suffer two key issues: 1) only focusing…

机器学习 · 计算机科学 2022-01-03 Dongbo Xi , Fuzhen Zhuang , Bowen Song , Yongchun Zhu , Shuai Chen , Dan Hong , Tao Chen , Xi Gu , Qing He

Non-uniform image deblurring is a challenging task due to the lack of temporal and textural information in the blurry image itself. Complementary information from auxiliary sensors such event sensors are being explored to address these…

计算机视觉与模式识别 · 计算机科学 2022-08-25 Patricia Vitoria , Stamatios Georgoulis , Stepan Tulyakov , Alfredo Bochicchio , Julius Erbach , Yuanyou Li

Event-based cameras are vision devices that transmit only brightness changes with low latency and ultra-low power consumption. Such characteristics make event-based cameras attractive in the field of localization and object tracking in…

计算机视觉与模式识别 · 计算机科学 2020-10-30 Sherif A. S. Mohamed , Jawad N. Yasin , Mohammad-hashem Haghbayan , Antonio Miele , Jukka Heikkonen , Hannu Tenhunen , Juha Plosila

Event-based cameras provide accurate and high temporal resolution measurements for performing computer vision tasks in challenging scenarios, such as high-dynamic range environments and fast-motion maneuvers. Despite their advantages,…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Mohammad Rostami , Dayuan Jian , Ruitong Sun

Because of their high temporal resolution, increased resilience to motion blur, and very sparse output, event cameras have been shown to be ideal for low-latency and low-bandwidth feature tracking, even in challenging scenarios. Existing…

计算机视觉与模式识别 · 计算机科学 2026-01-16 Nico Messikommer , Carter Fang , Mathias Gehrig , Giovanni Cioffi , Davide Scaramuzza

Spiking neural networks are powerful computational elements that pair well with event-based cameras (EBCs). In this work, we present two spiking neural network architectures that process events from EBCs: one that isolates and filters out…

神经与进化计算 · 计算机科学 2024-01-30 Charles P. Rizzo , Catherine D. Schuman , James S. Plank