PhD in Compressed Sensing for Egocentric Video

自我中心视频压缩感知博士

• 批准号: 2894973
• 金额: --
• 依托单位: University of Bristol
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2894973
• 关键词: PhD; Compressed; Sensing; Egocentric; Video

Computer vision has enjoyed much enrichment since the dawn of deep neural networks (DNNs). These improvements have largely arrived in the form of convo- lutional neural networks [2] (CNNs) or more recently, transformers [11]. Regardless of the form of the model, these techniques dominate fields where the aim is to auto- mate image and video understanding. One of the key challenges in computer vision is ensuring that the model is able to be implemented with convenient hardware (light and unobtrusive) that solves the problem in real-time. These physical constraints are compounded in the case of wearable technology, where current hardware is often unwieldy, large or expensive.

自深度神经网络 (DNN) 诞生以来，计算机视觉得到了极大的丰富。这些改进主要以卷积神经网络 [2] (CNN) 或最近的 Transformer [11] 的形式实现。无论模型的形式如何，这些技术在以自动化图像和视频理解为目标的领域中占据主导地位。计算机视觉的关键挑战之一是确保模型能够使用方便的硬件（轻便且不引人注目）来实现，从而实时解决问题。在可穿戴技术中，这些物理限制更加复杂，当前的硬件通常笨重、庞大或昂贵。