A time-series classification challenge is organized in the context of the workshop.

Participants are given a training set of labeled multivariate time series (train.h5) representing isolated gestures captured with a Kinect system by different users.

Two tasks are considered:

  • Task 1 is a standard Time Series Classification task, for which test_task1.h5 should be used ;
  • Task 2 adds time series spotting to the challenge: test time series (provided in test_task2.h5) are the concatenation of different gestures and participants are asked to spot both the gesture classes that form the time series and their locations.

The best teams will have the opportunity to present their methods in a special session during the workshop.

For more information or for participating to this challenge, send a mail to Romain Tavenard (romain[dot]tavenard[at]univ-rennes2[dot]fr) and Simon Malinowski (simon[dot]malinowski[at]irisa[dot]fr).

Data sets are the property of IRISA, research team EXPRESSION.  Participants of the challenge are committed not to divulgate it.

Important dates

The official leaderboard (using the full test set) for this challenge will be built based on the results provided before September, 1st, 2016.

Based on this leaderboard, best teams will be offered the opportunity to present their methods during the workshop.

Official leaderboard

The following leaderboard has been computed on the whole test set.

Task 1

Rank Team name Method name Accuracy Number of submitted
runs (max. 10)
1. UCRDMYeh bofSC + randShape 0.961 1
2. Mustafa Baydogan SMTS 0.956 3
Lemaire-Boullé, Orange Labs Automatic Feature Construction +
Selective Naive Bayes
0.956 2
4. HU-WBI MWSL 0.950 3
5. CIML RC 0.944 3
UCRDMYeh convNet 0.944 1
UCRDMYeh bofSC 0.944 1
8. UEA COTE 0.939 4
9. UEA HESCA 0.933 2
Josif Grabocka LearningShapelets 0.933 1
11. UCRDM pDTWKerSVM + RandSub 0.928 2
UEA Rotation Forest Benchmark 0.928 3
13. HU-WBI BOSS 0.911 4
14. DDIG Softmax+RandShapes 0.906 1
15. HU-WBI BOSS-DTW 0.894 2
16. SAMAS GK-kNC 0.889 2
17. UCRDMYeh randShape 0.883 3
18. Baseline DTW-1NN 0.872
19. WP-lab MsV 0.861 2
20. WP-lab MsV+csp+lr 0.839 1
Baseline ED-1NN 0.839
22. WP-lab MsV+csp 0.833 2
23. AMA-IKATS Classification trees for time series 0.800 1
24. BogaziciUni mv-ARF 0.789 2

Task 2

The evaluation method is based on an edit distance that enables first to align two sequences of labeled temporal segments, and then, by back-tracing an optimal alignment path, to provide a confusion matrix at the label level. From this confusion matrix, standard evaluation measures such as precision, recall and F1 measures can easily be derived as well as other measures such as the ”latency” of the detection that can be quite important in pattern (early) detection applications. For this ranking, F1 measure is used.

Rank Team name Method name F1 Number of submitted
runs (max. 10)
1. UCRDMYeh bofSC + randShape 0.959 1
UCRDM pDTWKerSVM + RandSub 0.959 2
3. UCRDMYeh bofSC 0.956 2
4. UCRDMYeh randShape 0.865 2

 Data format

Data is distributed as HDF5 files (train.h5test_task1.h5 and test_task2.h5). Sample code for reading these files is provided for Python (here) and R (here). Matlab users should be able to adapt this code for their scripts using hdf5read.

Datasets are 3-dimensional arrays of size (n, t, d) where n is the number of time series, t the number of time instants and d the number of features (i.e. number of sensors x 3 here). Hence, each time series is a matrix of t rows and d (= 24 = 8 sensors * 3) columns. Column ordering is as follows:

1. Hand tip left, X coordinate
2. Hand tip left, Y coordinate
3. Hand tip left, Z coordinate
4. Hand tip right, X coordinate
5. Hand tip right, Y coordinate
6. Hand tip right, Z coordinate
7. Elbow left, X coordinate
8. Elbow left, Y coordinate
9. Elbow left, Z coordinate
10. Elbow right, X coordinate
11. Elbow right, Y coordinate
12. Elbow right, Z coordinate
13. Wrist left, X coordinate
14. Wrist left, Y coordinate
15. Wrist left, Z coordinate
16. Wrist right, X coordinate
17. Wrist right, Y coordinate
18. Wrist right, Z coordinate
19. Thumb left, X coordinate
20. Thumb left, Y coordinate
21. Thumb left, Z coordinate
22. Thumb right, X coordinate
23. Thumb right, Y coordinate
24. Thumb right, Z coordinate


Each team (i.e. each pair research group / method) is allowed to submit up to 10 runs per task. Unless otherwise stated, the last submitted run will always be the one considered for the ranking.

Task 1

To submit a run, one should send organizers a mail with results attached in a text file containing predicted classes for test time series, one per row, such as:


Task 2

To submit a run, one should send organizers a mail with results attached in a text file containing predicted classes for test time series (one row per test time series, 6 gestures per row) and their start/end times, such as:

5:0-65 2:66-71 3:72-112 5:113-164 6:165-220 2:224-305 # Occurrence of class 5 detected in frames 0 to 65, etc. 

Note that there should be no overlap between predictions and predictions should be ordered by increasing starting time.

Comments are closed