Center for Research in Comptuer Vision
Center for Research in Comptuer Vision



Data Sets

UCF101 - Action Recognition Data Set


There will be a workshop in ICCV'13 with UCF101 as its main competition benchmark: The First International Workshop on Action Recognition with Large Number of Classes.

Click here to check the published results on UCF101 (updated October 17, 2013)

UCF101 is an action recognition data set of realistic action videos, collected from YouTube, having 101 action categories. This data set is an extension of UCF50 data set which has 50 action categories.

With 13320 videos from 101 action categories, UCF101 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, UCF101 aims to encourage further research into action recognition by learning and exploring new realistic action categories.

The videos in 101 action categories are grouped into 25 groups, where each group can consist of 4-7 videos of an action. The videos from the same group may share some common features, such as similar background, similar viewpoint, etc.

The action categories can be divided into five types: 1)Human-Object Interaction 2) Body-Motion Only 3) Human-Human Interaction 4) Playing Musical Instruments 5) Sports.

The action categories for UCF101 data set are: Apply Eye Makeup, Apply Lipstick, Archery, Baby Crawling, Balance Beam, Band Marching, Baseball Pitch, Basketball Shooting, Basketball Dunk, Bench Press, Biking, Billiards Shot, Blow Dry Hair, Blowing Candles, Body Weight Squats, Bowling, Boxing Punching Bag, Boxing Speed Bag, Breaststroke, Brushing Teeth, Clean and Jerk, Cliff Diving, Cricket Bowling, Cricket Shot, Cutting In Kitchen, Diving, Drumming, Fencing, Field Hockey Penalty, Floor Gymnastics, Frisbee Catch, Front Crawl, Golf Swing, Haircut, Hammer Throw, Hammering, Handstand Pushups, Handstand Walking, Head Massage, High Jump, Horse Race, Horse Riding, Hula Hoop, Ice Dancing, Javelin Throw, Juggling Balls, Jump Rope, Jumping Jack, Kayaking, Knitting, Long Jump, Lunges, Military Parade, Mixing Batter, Mopping Floor, Nun chucks, Parallel Bars, Pizza Tossing, Playing Guitar, Playing Piano, Playing Tabla, Playing Violin, Playing Cello, Playing Daf, Playing Dhol, Playing Flute, Playing Sitar, Pole Vault, Pommel Horse, Pull Ups, Punch, Push Ups, Rafting, Rock Climbing Indoor, Rope Climbing, Rowing, Salsa Spins, Shaving Beard, Shotput, Skate Boarding, Skiing, Skijet, Sky Diving, Soccer Juggling, Soccer Penalty, Still Rings, Sumo Wrestling, Surfing, Swing, Table Tennis Shot, Tai Chi, Tennis Swing, Throw Discus, Trampoline Jumping, Typing, Uneven Bars, Volleyball Spiking, Walking with a dog, Wall Pushups, Writing On Board, Yo Yo.

The UCF101 data set can be downloaded by clicking here.

The Train/Test Splits for Action Recognition on UCF101 data set can be downloaded by clicking here.

The Train/Test Splits for Action Detection on UCF101 data set can be downloaded by clicking here.

The STIP Features for UCF101 data set can be downloaded here: Part1 Part2.

If you use this data set, please refer to the following technical report:
Khurram Soomro, Amir Roshan Zamir and Mubarak Shah, UCF101: A Dataset of 101 Human Action Classes From Videos in The Wild., CRCV-TR-12-01, November, 2012.

For questions regarding this data set, please contact Khurram Soomro (khurram [at] knights.ucf.edu).




Statistics











Results on UCF101

If you happen to use UCF101, send us an email with the following details and we will update our webpage with your results.



Performance Experimental Setup Paper
43.90%
Three Train/Test Splits
Soomro, et al.
(CRCV-TR-12-01),2012

Note: It is very important to keep the videos belonging to the same group seperate 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.

Related Publication

Khurram Soomro, Amir Roshan Zamir and Mubarak Shah, UCF101: A Dataset of 101 Human Action Classes From Videos in The Wild, CRCV-TR-12-01, November, 2012.