2014 Looking At People ECCV Challenge

Challenge description

ChaLearn organizes in 2014 three parallel challenge tracks on Human Pose Recovery on RGB data, action/interaction spotting on RGB data, and gesture spotting on RGB-Depth data.

The challenge features three quantitative tracks:

Track 1: Human Pose Recovery: More than 8,000 frames of continuous RGB sequences are recorded and labeled with the objective of performing human pose recovery by means of recognizing more than 120,000 human limbs of different people. Examples of labeled frames are shown in Fig. 1.

Track 2: Action/Interaction Recognition: 235 performances of 11 action/interaction categories are recorded and manually labeled in continuous RGB sequences of different people performing natural isolated and collaborative actions randomly. Examples of labeled actions are shown in Fig. 1.

Track 3: Gesture Recognition: More than 14,000 gestures are drawn from a vocabulary of 20 Italian sign gesture categories. The emphasis of this third track is on multi-modal automatic learning of a set of 20 gestures performed by several different users, with the aim of performing user independent continuous gesture spotting. An example of the visual modalities for each frame of the data set is shown in Fig.2. 

Figure 1: Samples of the RGB Human Pose Recovery and Action/Interaction tracks
 

Figure 2: Samples of the RGBD gesture spotting track

Top three ranked participants on each track will be awarded and invited to follow the ECCV workshop submission guide for inclusion of a description of their system at the ECCV proceedings and submit an extended paper in a special issue on gesture recognition at a Special Issue of the TPAMI journal.