论文速读 - 移动计算中基于VM的Cloudlet案例
Published:
移动计算还未真正挖掘其潜力，因此文章提出一种全新的架构。
Posts by Tags
Edge Computing
Few-shot learning
Image Classification Based on Few-Shot Learning
Published:
This blog classifies and summarizes the current image classification algorithms based on Few-shot learning. According to the modeling methods of different data types, Few-shot image classification algorithms are divided into convolution neural network model and graph neural network model. Convolution neural network model is divided into four learning paradigms: transfer learning, meta learning, Bayesian learning and dual learning. Two kinds of algorithms are introduced in detail. Finally, for the current Few-shot image classification algorithm, we discuss the ethical oriented implications in terms of interpretability and privacy.
Research Proposal
Temporal action localization with Semi-Supervised Learning
Published:
Temporal action localization is an important task in the field of video content analysis, and its goal is to locate the action instances with precise boundaries and flexible intervals in an untrimmed video. Constructing a large enough data set that contains video clips and annotations will require vast human effort. Since there are quite many unlabeled videos on the internet, it is worth trying to combine semi-supervised approaches into temporal action localization task.
attention mechanism
探秘计算机视觉中的注意力机制
Published:
近年来，越来越多的工作专注于将注意力机制融入计算机视觉任务中。本文重点介绍注意力机制的基本原理和利用飞桨实现注意力机制的基本方法。
computer vision
Image Classification Based on Few-Shot Learning
Published:
This blog classifies and summarizes the current image classification algorithms based on Few-shot learning. According to the modeling methods of different data types, Few-shot image classification algorithms are divided into convolution neural network model and graph neural network model. Convolution neural network model is divided into four learning paradigms: transfer learning, meta learning, Bayesian learning and dual learning. Two kinds of algorithms are introduced in detail. Finally, for the current Few-shot image classification algorithm, we discuss the ethical oriented implications in terms of interpretability and privacy.
Temporal action localization with Semi-Supervised Learning
Published:
Temporal action localization is an important task in the field of video content analysis, and its goal is to locate the action instances with precise boundaries and flexible intervals in an untrimmed video. Constructing a large enough data set that contains video clips and annotations will require vast human effort. Since there are quite many unlabeled videos on the internet, it is worth trying to combine semi-supervised approaches into temporal action localization task.
探秘计算机视觉中的注意力机制
Published:
近年来，越来越多的工作专注于将注意力机制融入计算机视觉任务中。本文重点介绍注意力机制的基本原理和利用飞桨实现注意力机制的基本方法。
ActivityNet Challenge 2019 冠军模型BMN算法全解析
Published:
随着互联网世界视频数量的急剧增长，视频内容分析技术得到了越来越广泛关注。视频动作定位是视频内容分析领域里的一个重要任务，它的目标是在一段未经修剪的视频中定位出动作类别及其对应的时序边界。通常视频动作定位任务可以分为两个阶段：时序提名生成和动作分类。本文所介绍的算法BMN为百度自研，为时序提名生成任务提供了一个高效的解决方案，是ActivityNet2019大赛中的task1和task2的冠军方案（task1为时序提名生成，task2为视频动作定位）。
deep learning
Image Classification Based on Few-Shot Learning
Published:
This blog classifies and summarizes the current image classification algorithms based on Few-shot learning. According to the modeling methods of different data types, Few-shot image classification algorithms are divided into convolution neural network model and graph neural network model. Convolution neural network model is divided into four learning paradigms: transfer learning, meta learning, Bayesian learning and dual learning. Two kinds of algorithms are introduced in detail. Finally, for the current Few-shot image classification algorithm, we discuss the ethical oriented implications in terms of interpretability and privacy.
Temporal action localization with Semi-Supervised Learning
Published:
Temporal action localization is an important task in the field of video content analysis, and its goal is to locate the action instances with precise boundaries and flexible intervals in an untrimmed video. Constructing a large enough data set that contains video clips and annotations will require vast human effort. Since there are quite many unlabeled videos on the internet, it is worth trying to combine semi-supervised approaches into temporal action localization task.
探秘计算机视觉中的注意力机制
Published:
近年来，越来越多的工作专注于将注意力机制融入计算机视觉任务中。本文重点介绍注意力机制的基本原理和利用飞桨实现注意力机制的基本方法。
ActivityNet Challenge 2019 冠军模型BMN算法全解析
Published:
随着互联网世界视频数量的急剧增长，视频内容分析技术得到了越来越广泛关注。视频动作定位是视频内容分析领域里的一个重要任务，它的目标是在一段未经修剪的视频中定位出动作类别及其对应的时序边界。通常视频动作定位任务可以分为两个阶段：时序提名生成和动作分类。本文所介绍的算法BMN为百度自研，为时序提名生成任务提供了一个高效的解决方案，是ActivityNet2019大赛中的task1和task2的冠军方案（task1为时序提名生成，task2为视频动作定位）。
深度学习 训练集与验证集损失分析
Published:
深度学习中，如何对训练集与验证集上的Loss变化进行正确的分析，并进行妥当的改善？
paper reading
论文速读 - 移动计算中基于VM的Cloudlet案例
Published:
移动计算还未真正挖掘其潜力，因此文章提出一种全新的架构。
temporal action detection
ActivityNet Challenge 2019 冠军模型BMN算法全解析
Published:
随着互联网世界视频数量的急剧增长，视频内容分析技术得到了越来越广泛关注。视频动作定位是视频内容分析领域里的一个重要任务，它的目标是在一段未经修剪的视频中定位出动作类别及其对应的时序边界。通常视频动作定位任务可以分为两个阶段：时序提名生成和动作分类。本文所介绍的算法BMN为百度自研，为时序提名生成任务提供了一个高效的解决方案，是ActivityNet2019大赛中的task1和task2的冠军方案（task1为时序提名生成，task2为视频动作定位）。