ChaLearn gesture challenge: Design and first results

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

99 citations recorded by the source corpus.

How researchers see this paper

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

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).”
Human gesture recognition on product manifolds (2012, methodology): “To facilitate the adaptation to new gestures, CHALEARN (Guyon et al., 2012) has organized a one-shot-learning challenge for gesture recognition.”
One-Shot Learning for Real-Time Action Recognition (2013, methodology): “We have defined two different datasets: in the first one the lexicon is composed of numbers performed with fingers, in the second one we tried to replicate one of the lexicons of the ChaLearn Gesture Dataset where we got the worst results, namely the devel 3.”
One-shot learning gesture recognition from RGB-D data using bag of features (2013, methodology): “2 Metric of Evaluation We adopt the metric of evaluation that was used by the challenge organizers (Guyon et al., 2012) to rank the entries.”
Human-Computer Interaction. Advanced Interaction Modalities and Techniques (2014, methodology): “[29] Showed that object tracking based on color information is possible with a method called CamShift which is based on the mean shift algorithm.”
Online action recognition using covariance of shape and motion (2014, methodology): “OneShot-Learning gesture challenge [16], was to recognize a specific gesture from a vocabulary of 8–15 gestures, based on a single example for each gesture from the vocabulary.”
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition (2014, background): “A number of new datasets [6, 7, 8, 28] have provided researchers with the opportunity to design novel representations and algorithms and test them on a much larger number of sequences.”
A Survey of Datasets for Human Gesture Recognition (2014, background): “CGD2011 [29] ChaLearn Dataset 2HA FV St.”
3D SMoSIFT: three-dimensional sparse motion scale invariant feature transform for activity recognition from RGB-D videos (2014, unknown): “Journal of Electronic Imaging 023017-8 Mar–Apr 2014 • Vol. 23(2) 4.3 CGD A comprehensive dataset of human actors performing a variety of gestures has been made available to researchers under Microsoft ChaLearn Gesture Challenge.29 The goal of the challenge is to employ systems to perform gesture rec”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “Recently, ChaLearn gesture dataset [174] and G3D, a gaming dataset [175], concentrated on continuous actions.”
Towards Deep Developmental Learning (2016, background): “Here again, a lot of effort is dedicated to these concerns in the deep learning literature, with the same methodological limitations as above [85], [86].”
Domain-Adaptive Discriminative One-Shot Learning of Gestures (2014, background): “As a result, several recent works have attempted to learn gestures at the other extreme – from single training examples using one-shot learning [16,17,19,20,22,24,33].”