Results and Analysis of the ChaLearn Gesture Challenge 2012

By Isabelle M Guyon, Vassilis Athitsos, Pat Jangyodsuk, Hugo Jair Escalante, B. Hamner. 2012

53 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Oscar Koller
2. Richard Bowden
3. Necati Cihan Camgöz
4. Simon Hadfield
5. Michal Hagara
6. Jakub Konecný
7. Debin Zhao
8. Feng Jiang

In Control and Systems Engineering

1. Michael Firman
2. Q. Ruan
3. Feng Jiang
4. Richard Bowden
5. Debin Zhao
6. Shengping Zhang
7. Jun Wan
8. Michal Hagara

In Human-Computer Interaction

1. Oscar Koller
2. Necati Cihan Camgöz
3. Richard Bowden
4. Simon Hadfield
5. Michal Hagara
6. Jakub Konecný
7. Michael Firman
8. Q. Ruan

Citations in the corpus

• One-shot-learning gesture recognition using HOG-HOF features (2013, methodology): “The methods used by other challenge participants — alfnie, Pennect, Joewan (Wan et al., 2013), OneMillionMonkeys, Manavender (Malgireddy et al., 2012) — are summarized by Guyon et al. (2012, 2013).”
• One-shot learning gesture recognition from RGB-D data using bag of features (2013, methodology): “We adopt the metric of evaluation that was used by the challenge organizers (Guyon et al., 2012) to rank the entries.”
• RGBD Datasets: Past, Present and Future (2016, background): “while the Manipulation Action Dataset [1] is unique in providing semantic segmentation of objects as they are manipulated. By far the largest gesture dataset is the ChaLearn gesture challenge dataset [49], with 50,000 videos of around 850 different gestures. Many of these datasets suffer from being ”
• 3D SMoSIFT: three-dimensional sparse motion scale invariant feature transform for activity recognition from RGB-D videos (2014, methodology): “The top ranking methods were introduced by Guyon et al.30 Besides, we also compared the proposed feature with 3D (E)MoSIFT.”
• Multi-layered gesture recognition with Kinect (2015, methodology): “…for gesture recognition in which SOFM is used as an implicit feature extractor for continuous HMM. Recently, Wan et al. (2012a) proposes ScHMM to deal with the gesture recognition where sparse coding is adopted to find succinct representations and Lagrange dual is applied to obtain a codebook.”
• Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition (2016, methodology): “We have applied the proposed method to the ConGD dataset, which was introduced with the ChaLearn 2016 Continuous Gesture Recognition Challenge, and ranked 2nd with a model which was fine-tuned for 11,250 iterations.”