Details
-
The sequences describe the following 6 different
types of human actions performed by 25 subjects in 4 different
scenarios:
- Walking
Download video
- Jogging
Download video
- Running
Download video
- Boxing
Download video
- Hand Waving
Download video
- Hand Clapping
Download video
- Sample sequences for each action (DivX-compressed)
- person15 Walking
Download video
- person15 Jogging
Download video
- person15 Running
Download video
- person15 Boxing
Download video
- person15 Hand Waving
Download video
- person15 Hand Clapping
Download video
- All the above sequences have a frame rate of 25 fps and
were downsampled to a resolution of 160x120 pixels, having a length of 4 seconds
in average. Moreover, all sequences were divided into a training set (8
persons), a validation set (8 persons) and a test set (9 persons) according with
their subjects. The classifiers were trained on a training set while the
validation set was used to optimize the parameters of each method. The
recognition results were obtained on the test set.
Related papers
-
Recognizing Human Actions: A Local SVM Approach, Christian
Schuldt, Ivan Laptev and Barbara Caputo; in Proc. ICPR'04, Cambridge, UK.
Download PDF
-
Local Spatio-Temporal Image Features for Motion
Interpretation, Ivan Laptev; PhD Thesis, 2004, Computational Vision and Active
Perception Laboratory (CVAP), NADA, KTH, Stockholm
Download PDF
-
Local Descriptors for Spatio-Temporal Recognition, Ivan
Laptev and Tony Lindeberg; ECCV Workshop Spatial Coherence for Visual Motion
Analysis
Download PDF
-
Velocity adaptation of space-time interest points, Ivan
Laptev and Tony Lindeberg; in Proc. ICPR'04, Cambridge, UK
Download PDF
-
Space-Time Interest Points, Ivan Laptev and Tony Lindeberg;
in Proc. ICCV'03, Nice, France
Download PDF
Evaluation Protocol
-
There are 600 video files for each combination of
25 subjects, 6 actions and 4 scenarios. Each file contains about 4
subsequences used as a sequence in these experiments. The subdivision of
each file into sequences in terms start_frame and end_frame as well as
the list of all sequences is given in following txt file: sequences.txt
Download
Features and top scores
| Method:
| [Paper Name] | [Paper Name] |
| Score:
| | |