ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition

By Jun Wan, S. Li, Yibing Zhao, Shuai Zhou, Isabelle M Guyon, Sergio Escalera. 2016

247 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental and Educational Psychology, 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 Developmental and Educational Psychology

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): “For ChaLearn LAP IsoGD Dataset, in order to minimize the interference of the background, it is assumed that the background in the histogram of depth maps occupies the last peak representing far distances.”
Large-scale Isolated Gesture Recognition using pyramidal 3D convolutional networks (2016, methodology): “In this section, the ChaLearn Looking at People RGB-D Isolated Gesture Dataset (IsoGD) [7] will be introduced briefly; then the details of the training and testing processes of the proposed framework will be described; at last, the validation and testing results will be reported.”
A Unified Framework for Multi-Modal Isolated Gesture Recognition (2018, methodology): “It is more preferable than 3DDSN-RGB (62.72% vs 46.08% on ChaLearn IsoGD and 96.13% vs 94.23% on RGBD-HuDaACt), therefore 3DDSN-RGB is not included in our ﬁnal framework.”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, background): “For instance, the large-scale isolated gesture recognition challenge [24] has on average only 144 video clips per class compared to 1200 images per class in ImageNet.”
Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model (2016, methodology): “As similar gestures are integrated with the unique label [2], the challenges we encounter are all aforementioned except for the gesture ambiguity.”
Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition (2016, methodology): “The training of SVM takes about 6 hours and the accuracy on IsoGD [36] is 53.”
Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition (2016, methodology): “in [25] for the ChaLearn 2016 Continuous Gesture Recognition Challenge and a baseline was presented for the dataset which uses Mixed Features around Sparse Keypoints (MFSK) and Bag of Visual Words based approach (See Table II).”
ChaLearn looking at people: A review of events and resources (2017, methodology): “ated: ChaLearn LAP RGB-D Continuous Gesture Dataset (ConGD) is considered for this track [11].”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, background): “For instance, the large-scale isolated gesture recognition challenge [19] has on average only 144 video clips per class”
EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition (2018, methodology): “Cambridge Hand Gesture Dataset 2007 [3] 900 9 2 1 RGB classification second-person MSRGesture3D 2012 [5] 336 12 10 1 RGB-D classification second-person ChAirGest 2013 [13] 1,200 10 10 1 RGB-D, IMU classification second-person SKIG 2013 [4] 1,080 10 6 3 RGB-D classification second-person ChaLearn MMG”
Two streams Recurrent Neural Networks for Large-Scale Continuous Gesture Recognition (2016, methodology): “MFSK and MFSK+DeepIDare [5], are also taken as the comparisons for the previous evaluations on the ConGD.”
Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM (2017, methodology): “The 249 kinds of gestures include: 1) body language gestures, 2) gesticulations performed to accompany speech, 3) illustrators like Italian gestures, 4) emblems like Indian Mudras, 5) sign languages for the deaf, 6) signals, 7) actions, 8) pantomimes, and 9) dance postures [1], [6].”