Abstract | ||
---|---|---|
This paper summarizes the ChaLearn Looking at People 2014 challenge data and the results obtained by the participants. The competition was split into three independent tracks: human pose recovery from RGB data, action and interaction recognition from RGB data sequences, and multi-modal gesture recognition from RGB-Depth sequences. For all the tracks, the goal was to perform user-independent recognition in sequences of continuous images using the overlapping Jaccard index as the evaluation measure. In this edition of the ChaLearn challenge, two large novel data sets were made publicly available and the Microsoft Codalab platform were used to manage the competition. Out-standing results were achieved in the three challenge tracks, with accuracy results of 0.20, 0.50, and 0.85 for pose recovery, action/interaction recognition, and multi-modal gesture recognition, respectively. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-16178-5_32 | COMPUTER VISION - ECCV 2014 WORKSHOPS, PT I |
Keywords | Field | DocType |
Human pose recovery, Behavior analysis, Action and interactions, Multi-modal gestures, Recognition | Computer vision,Data set,Computer science,Gesture recognition,RGB color model,Data sequences,Artificial intelligence,Jaccard index,Machine learning | Conference |
Volume | ISSN | Citations |
8925 | 0302-9743 | 62 |
PageRank | References | Authors |
1.74 | 15 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sergio Escalera | 1 | 1415 | 113.31 |
Xavier Baró | 2 | 474 | 33.99 |
Jordi Gonzalez | 3 | 617 | 48.02 |
Miguel Ángel Bautista | 4 | 168 | 10.97 |
Meysam Madadi | 5 | 87 | 9.28 |
Miguel Reyes | 6 | 264 | 10.08 |
Víctor Ponce-López | 7 | 132 | 7.10 |
Hugo Jair Escalante | 8 | 939 | 73.89 |
Jamie Shotton | 9 | 7571 | 324.72 |
Isabelle Guyon | 10 | 11033 | 1544.34 |