Multi-modal gesture recognition challenge 2013: dataset and results

By Sergio Escalera, Jordi Gonzàlez, Xavier Baró, Miguel Reyes, Oscar Lopes, Isabelle M Guyon, Vassilis Athitsos, Hugo Jair Escalante. 2013

206 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental and Educational Psychology, Multimodal Learning, Evaluation & Benchmarks, 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. Luc Van Gool
2. G. Wang
3. Liang Wang
4. Dacheng Tao
5. Jun Liu
6. Xiaogang Wang
7. Ming-Hsuan Yang
8. Yi Yang

In Developmental and Educational Psychology

1. Liang Wang
2. Hongsong Wang
3. Sergio Escalera
4. Isabelle M Guyon
5. Jun Liu
6. Ling Shao
7. Jun Wan
8. Di Wu

In Multimodal Learning

1. Liang Wang
2. Hongsong Wang
3. Jun Liu
4. G. Wang
5. Alex ChiChung Kot
6. Amir Shahroudy
7. Martin Saerbeck
8. P. PramodKumar

In Evaluation & Benchmarks

1. Liang Wang
2. Hongsong Wang
3. Jun Liu
4. Alex ChiChung Kot
5. Amir Shahroudy
6. G. Wang
7. Dong Xu
8. Jun Wan

In Human-Computer Interaction

1. Sergio Escalera
2. Liang Wang
3. Isabelle M Guyon
4. Hongsong Wang
5. Jun Wan
6. Shuai Zhou
7. S. Li
8. Jun Liu

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other datasets captured using a Kinect v1 camera were also released to the public, including the MSR Daily Activity 3D [121], MSR Action Pairs [113], Online RGBD Action (ORGBD) [107], UTKinect-Action [124], Florence 3D-Action [118], CMU-MAD [104], UTD-MHAD [103], G3D/G3Di [105], [119], SPHERE [”
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “ChaLearn Gesture Dataset [73] consists of 23 hours of videos captured with Kinect.”
• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “As done in the literature [9, 12], we report the precision, recall and F1-score measures on the validation set.”
• Adaptive RNN Tree for Large-Scale Human Action Recognition (2017, methodology): “Further, we create a large-scale SAR dataset that has 140 action classes, which we term as 3D-SAR-140, by aggregating and processing 10 existing smaller-scale datasets [3, 5, 6, 12, 14, 15, 16, 25, 27, 28].”
• ChaLearn looking at people: A review of events and resources (2017, background): “2013 Looking at People ICMI Challenge: ChaLearn LAP organized in 2013 a challenge and workshop on multi-modal gesture recognition from 2D and 3D video data using Kinect [4].”
• ChaLearn Looking at People Challenge 2014: Dataset and Results (2014, methodology): “Two large datasets (HuPBA8K and Montalbano datasets) were designed, manually-labeled, and made publicly available to the participants for 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 60”
• Recent methods and databases in vision-based hand gesture recognition: A review (2015, methodology): “ChaLearn Multi-modal Gesture Data In comparison to the ChaLearn gesture data, the testing using ChaLearn multi-modal gesture data [128] is more challenging.”
• ChaLearn Looking at People and Faces of the World: Face AnalysisWorkshop and Challenge 2016 (2016, methodology): “Following previous series on Looking at People (LAP) competitions [14, 13, 9, 12, 4, 10, 42, 15], in 2016, ChaLearn and Faces of the World organized new competitions and workshops on automatic face analysis in still images.”
• Modeling video evolution for action recognition (2015, background): “Table 5: Detailed analysis of precision and recall on the ChaLearn gesture recognition dataset [2]”
• Rank Pooling for Action Recognition (2015, methodology): “ChaLearn Gesture Recognition dataset [9].”
• 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.”
• Two streams Recurrent Neural Networks for Large-Scale Continuous Gesture Recognition (2016, background): “To evaluate the gesture recognition algorithms objectively and fairly, some research groups released several gesture databases [3]–[8].”
• Skeleton based action recognition with convolutional neural network (2015, methodology): “ChaLearn Gesture Recognition Dataset [2]: It is the ChaLearn 2013 Multi-model gesture dataset, which contains 23 hours of Kinect data with 27 persons performing 20 Italian gestures.”
• Hierarchical motion evolution for action recognition (2015, methodology): “The ChaLearn 2013 Gesture dataset [4] contains 23 hours of Kinect data of 27 persons performing 20 Italian gestures.”