G015.mp4 | Original 2027 |

Researchers use this dataset to train models (like 3D CNNs or Transformers) to: Identify what action is happening in a video.

It includes variations in camera motion, object appearance, scale, and background. Common Action Categories in the "G01" Series:

If your file is labeled v_ApplyEyeMakeup_g01_c05.mp4 (often shortened to g01 or g015 in certain processing scripts), it belongs to the category. Other common actions include: Archery Basketball Biking Cliff Diving Ice Dancing 🛠️ How it is Used Today g015.mp4

The file naming convention in this dataset follows a specific structure: v_[ActionName]_g[GroupNumber]_c[ClipNumber].mp4 . 101 distinct classes. Structure: Videos are divided into 25 groups per action. Source: All videos were collected from YouTube .

I can provide the or pre-trained weights if you are working with a particular framework like PyTorch or TensorFlow. Researchers use this dataset to train models (like

The video file is a specific sample from the UCF101 dataset, one of the most famous benchmarks in computer vision for action recognition. 📄 Associated Research Paper

when the action starts and ends (Temporal Localization). Source: All videos were collected from YouTube

The foundational paper for this dataset is: