MTEB logo MTEB
classification image

UCF101

Cite this task

@misc{soomro2012ucf101dataset101human,
  archiveprefix = {arXiv},
  author = {Khurram Soomro and Amir Roshan Zamir and Mubarak Shah},
  eprint = {1212.0402},
  primaryclass = {cs.CV},
  title = {UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild},
  url = {https://arxiv.org/abs/1212.0402},
  year = {2012},
}

UCF101 is an action recognition data set of realistic action videos collected from YouTube, having 101 action categories. This version of the dataset does not contain images but images saved frame by frame. Train and test splits are generated based on the authors' first version train/test list.

Domains: ActivitySportWeb
Languages: English
Task type
ImageClassification
Main metric
accuracy
Source dataset
mteb/ucf101
License
not specified
Dates
2012-01-01 → 2012-12-01
Annotations
derived
Sample creation
created
Models scored …
Dataset preview mteb/ucf101 Open on HuggingFace →

Model scores

Loading…