Welcome to the VIVA Hand Tracking Challenge!

try

try31

s


Welcome to the VIVA hand tracking benchmark! There are 27 training and 29 testing sequences. 2D bounding box annotations of hands are provided. Evaluation metrics are standard, and follow from
[1] K. Bernardin, R. Stiefelhagen, Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. JIVP, 2008.
[2] Y. Li, C. Huang, R. Nevatia, Learning to associate: HybridBoosted multi-target tracker for crowded scene. CVPR, 2009.
[3] A. Geiger, P. Lenz, C. Stiller, and R. Urtasun: Vision meets Robotics: The KITTI Dataset, IJRR, 2013.

Download the Training Videos. (3.2 GB)
Download the Training Annotations.
Download the Testing Videos. (2.38 GB)
Download the Testing Annotations.
Download Evaluation Tools.

ACF bounding boxes (the detection benchmark also provides the detection models) can be downloaded here.
Training Detection Boxes
Testing Detection Boxes

Result – Online Methods
Rank Method MOTA MOTP MT ML IDS FRAG Runtime* Environment
1 TDC (CNN) 25.1% 64.6% 39.1% 18.8% 34 415 4 fps 4 cores@3.5GHz, 16GB RAM
2 TDC (HOG) 24.6% 64.5% 35.9% 17.2% 39 426 4 fps 6 cores@3.5GHz, 32GB RAM, Titan X GPU

*Run-time does not include detection time.

Rank Publication
1 Rangesh, A., Ohn-Bar, E. & Trivedi, M.M. Long-term, Multi-Cue Tracking of Hands in Vehicles. IEEE Transactions on Intelligent Transportation Systems, 17(5):1483-1492, 2016.
2 Rangesh, A., Ohn-Bar, E. & Trivedi, M.M. Long-term, Multi-Cue Tracking of Hands in Vehicles. IEEE Transactions on Intelligent Transportation Systems, 17(5):1483-1492, 2016.
Result – Offline Methods
Rank Method MOTA MOTP MT ML IDS FRAG Runtime* Environment
1 TBD 6.75% 65.96% 50% 12.5% 29 320 0.1 fps 1 core@2.5GHz

*Run-time does not include detection time.

Rank Publication
1 Geiger, A., Lauer, M., Wojek, C., Stiller, C. & Urtasun, R. 3D Traffic Scene Understanding from Movable Platforms. Pattern Analysis and Machine Intelligence (PAMI), 2014.
Zhang, H., Geiger, A. & Urtasun, R. Understanding High-Level Semantics by Modeling Traffic Patterns. In International Conference on Computer Vision (ICCV), 2013.
(code)