Abstract
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.
Keywords
CLIPSUploadComputer scienceAction recognitionArtificial intelligenceAction (physics)Motion (physics)Baseline (sea)Human motionPattern recognition (psychology)Machine learningClass (philosophy)World Wide Web
Related Publications
Large-Scale Video Classification with Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Encouraged by these results, we provide an extensive emp...
Recognizing realistic actions from videos “in the wild”
In this paper, we present a systematic framework for recognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as w...
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal th...
Action recognition by dense trajectories
Feature trajectories have shown to be efficient for rep-resenting videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. Howeve...
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing dep...
Publication Info
- Year
- 2024
- Type
- preprint
- Volume
- 141
- Issue
- 5
- Pages
- 676-7
- Citations
- 4432
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
4432
OpenAlex
Cite This
Khurram Soomro,
Amir Zamir,
Mubarak Shah
(2024).
UCF-101: A dataset of 101 human actions classes from videos in the wild.
arXiv (Cornell University)
, 141
(5)
, 676-7.
https://doi.org/10.57702/46wax343
Identifiers
- DOI
- 10.57702/46wax343