Scholarlink

This chapter mainly introduces Differences Between Video Data and Image Data, Common Models (such as CNN + RNN, Two-Stream Network, 3D Convolutional Network, 3D Transformer), Pre-training Datasets (such as some public video datasets, such as HMDB51, UCF101, ActivityNet1.3, Charades, Kinetics400 and so on) and Task Introduction.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Computer Vision (Video): Theoretical Part

  • 章节

  • 发表日期：

    2026年

查看全文
  • Kele Xu

摘要

This chapter mainly introduces Differences Between Video Data and Image Data, Common Models (such as CNN + RNN, Two-Stream Network, 3D Convolutional Network, 3D Transformer), Pre-training Datasets (such as some public video datasets, such as HMDB51, UCF101, ActivityNet1.3, Charades, Kinetics400 and so on) and Task Introduction.