ChaLearn Joint Contest on Multimedia Challenges Beyond Visual Analysis: An overview

By Hugo Jair Escalante, Víctor Ponce-López, Jun Wan, Michael Alexander Riegler, Baiyu Chen, Albert Clapés, Sergio Escalera, Isabelle M Guyon, Xavier Baró, Pål Halvorsen and 2 more. 2016

89 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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

In Human-Computer Interaction

Citations in the corpus

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “hose two public benchmark datasets, which contain both RGB+depth modalities and have relatively large training samples to evaluate the proposed method. Speciﬁcally we chose ChaLearn LAP IsoGD Dataset [9] and M2I Dataset [34]. In the following, we proceed by brieﬂy describingthe implementationdetails”
Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition (2016, methodology): “We compare our proposed approach with competitors ranking top on the leaderboard of ChaLearn IsoGD benchmark [6, 36] and state-of-the-art results on RGB-HuDaAct [18] datasets.”
Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM (2017, background): “Convolutional neural networks (CNN) and RNN based methods have demonstrated the state-of-the-art performances on human gesture/action recognition [6], [32], [33].”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, methodology): “EXPERIMENTS In this section, the Large-scale Isolated Gesture Recogniti n Dataset at the ChaLearn LAP challenge 2016 (ChaLearn LAP IsoGD Dataset) [35] and the evaluation protocol are described.”
A Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences (2017, background): “…data sets that can cope with huge parametric deep models (e.g. [2, 38]) and on challenge organization (with novel data sets and well deﬁned evaluation protocols) that can advance the state-of-the-art of the ﬁeld and make easier the comparison among deep learning architectures (e.g. [92, 29]).”
Large-scale Isolated Gesture Recognition using pyramidal 3D convolutional networks (2016, methodology): “Our team obtains 50.93% accuracy on the test set and places third in the 2016 ChaLearn LAP Large-scale Isolated Gesture Recognition Challenge [32].”
Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model (2016, background): “Our approach achieves the accuracy of 49.2% on validation subset and 56.9% on the testing subset of the Chalearn LAP IsoGD Database respectively, and takes the first place of ChaLearn LAP Large-scale Isolated Gesture Recognition Challenge ultimately.”
Interpreting CNN Models for Apparent Personality Trait Regression (2017, background): “The First Impressions dataset [15, 8] consists of 10,000 clips extracted from more than 3, 000 different YouTube HD (720p) videos of people facing and speaking in English to a camera.”
Visualizing Apparent Personality Analysis with Deep Residual Networks (2017, methodology): “The first impressions data set was formerly used in the context of an academic challenge [10, 3] that aimed to develop methods for predicting the big 5 personality traits.”
ChaLearn looking at people: A review of events and resources (2017, background): “In the Challenges menu all organized and in progress competitions are listed.”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “44 on the ChaLearn LAP ConGD Dataset, which is higher than what the best result, i.e. 66 .”