With videos from action categories, UCF gives the largest diversity in terms of actions and with the presence of large variations in camera motion, object appearance and pose, object scale, viewpoint, cluttered background, illumination conditions, etc, it is the most challenging data set to date.
As most of the available action recognition data sets are not realistic and are staged by actors, UCF aims to encourage further research into action recognition by learning and exploring new realistic action categories. The videos in action categories are grouped into 25 groups, where each group can consist of videos of an action.
The videos from the same group may share some common features, such as similar background, similar viewpoint, etc. If you happen to use UCF, send us an email with the following details and we will update our web-page with your results.
Performance Experimental Setup Paper Note: It is very important to keep the videos belonging to the same group separate in training and testing.
Since the videos in a group are obtained from single long video, sharing videos from same group in training and testing sets would give high performance.
Data Set:. Click here. The videos from the same group may share some common features, such as similar background, similar viewpoint, etc. The UCF data set can be downloaded by clicking here. For questions regarding this data set, please contact Khurram Soomro khurram [at] knights.
Statistics Results on UCF If you happen to use UCF, send us an email with the following details and we will update our webpage with your results.
This would eliminate randomness in the experimental setup.
0コメント