Charades是由亚马逊的众包平台”土耳其机器人“收集的9848个日常室内活动视频组成的数据集。

Charades 是由通过 Amazon Mechanical Turk 收集的 9848 个日常室内活动视频组成的数据集。向 267 位不同的用户展示了一个句子，其中包括来自固定词汇表的对象和动作，他们录制了一段视频来执行该句子（就像在 Charades 游戏中一样）。该数据集包含 157 个动作类的 66,500 个时间注释、46 个对象类的 41,104 个标签以及视频的 27,847 个文本描述。这项工作在 ECCV2016 上进行了介绍。

• Each video has been exhaustively annotated using consensus from 4 workers on the training set, and from 8 workers on the test set. Please refer to the updated accompanying publication for details. Please contact vision.amt@allenai.org for questions about the dataset.

• Classification Performance

  AlexNet	11.2% mAP
  C3D	10.9% mAP
  Two-Stream	14.2% mAP
  IDT	17.2% mAP
  Combined	18.6% mAP
  Asynchronous Temporal Fields	22.4% mAP [*]

  (Uses the official Charades_v1_classify.m evaluation code. More details may be found in the README and the papers below.)

  ---

  Localization Performance

  Random	2.42% mAP
  VGG-16	7.89
  Two-Stream	8.94% mAP
  LSTM	9.60% mAP
  LSTM w/ post-processing	10.4% mAP
  Two-Stream w/ post-processing	10.9% mAP
  Asynchronous Temporal Fields	12.8% mAP [*]

  (Uses the official Charades_v1_localize.m evaluation code. More details may be found in the README and the papers below.)