UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

3 Dec 2012  ·  Khurram Soomro, Amir Roshan Zamir, Mubarak Shah ·

We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.

PDF Abstract

Datasets

Introduced in the Paper:

UCF101

Used in the Paper:

HMDB51 KTH
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition In Videos UCF101 Baseline UCF101 3-fold Accuracy 43.9 # 5
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy