Evaluation metrics

Evaluation Criteria

For the isolated gesture recognition, we calculate the recognition rate as the evaluation criteria. The recognition rate r:

                         r =  Number of correctly predict samples/ Number of samples


Submission format

In this track, the participants should submit a ZIP file containing only one text file named exactly as required below (do not add any folder in the ZIP). The ZIP file can be named randomly. Each line should contain three columns: name of M video, name of K video and the predicted label of that gesture video. The first two columns should be the same as the list file provieded with the database, and the third column is your prediction.

Note that: In the contest, you can use RGB, depth or RGB-D data as you want.

You can check this example out.

For Phase 1, the name of the prediction text file should be valid_prediction.txt .

For Phase 2, the final test phase, you could only submit your prediction once, and the name of the text file should be test_prediction.txt .

For example:

    valid/001/M_00001.avi valid/001/K_00001.avi 246
    valid/001/M_00002.avi valid/001/K_00002.avi 208
    valid/001/M_00003.avi valid/001/K_00003.avi 155
    valid/001/M_00004.avi valid/001/K_00004.avi 138
    valid/001/M_00005.avi valid/001/K_00005.avi 91


April 20: ICCV'17 competition started

Chalearn Coopetition on Action, Gesture, and Emotion Recognition started.