Linked e-resources
Details
Table of Contents
Foreword; Preface; Contents; 1 Challenges in Multi-modal Gesture Recognition; 1.1 Introduction; 1.2 Related Work in Gesture Recognition; 1.2.1 Taxonomy for Gesture Recognition; 1.2.2 Overview of Gesture Recognition Methods; 1.2.3 Sign Language Recognition; 1.2.4 Data Sets for Gesture and Action Recognition; 1.3 Gesture Recognition Challenges; 1.3.1 First ChaLearn Gesture Recognition Challenge (2011
2012): One Shot Learning; 1.3.2 ChaLearn Multimodal Gesture Recognition Challenge 2013; 1.3.3 ChaLearn Multimodal Gesture Spotting Challenge 2014
1.3.4 ChaLearn Action and Interaction Spotting Challenge 20141.3.5 ChaLearn Action and Interaction Spotting Challenge 2015; 1.3.6 Other International Competitions for Gesture and Action Recognition; 1.4 Summary of Special Topic Papers Not Related to the Challenges; 1.5 Summary of Special Topic Papers Related to 2011
2012 Challenges; 1.6 Summary of Special Issue Papers Related to 2013 Challenge; 1.7 Discussion; References; 2 Human Gesture Recognition on Product Manifolds; 2.1 Introduction; 2.2 Related Work; 2.3 Mathematical Background ; 2.3.1 Tensor Representation; 2.3.2 Orthogonal Groups
2.3.3 Stiefel Manifolds2.3.4 Grassmann Manifolds; 2.4 Elements of Product Manifolds ; 2.4.1 Product Manifolds; 2.4.2 Factorization in Product Spaces; 2.4.3 Geodesic Distance on Product Manifolds; 2.5 The Product Manifold Representation ; 2.6 Statistical Modeling; 2.6.1 Linear Least Squares Regression; 2.6.2 Least Squares Regression on Manifolds; 2.7 Experimental Results; 2.7.1 Cambridge Hand-Gesture Data Set; 2.7.2 UMD Keck Body-Gesture Data Set; 2.7.3 One-Shot-Learning Gesture Challenge; 2.8 Discussion; 2.9 Conclusions; References; 3 Sign Language Recognition Using Sub-units
3.1 Introduction3.2 Background; 3.2.1 Linguistics; 3.3 Learning Appearance Based Sub-units; 3.3.1 Location Features; 3.3.2 Motion and Hand-Arrangement Moment Feature Vectors; 3.3.3 Motion Binary Patterns and Additive Classifiers; 3.4 2D Tracking Based Sub-units; 3.4.1 Motion Features; 3.4.2 Location Features; 3.4.3 HandShape Features; 3.4.4 HandShape Classifiers; 3.5 3D Tracking Based Sub-units; 3.5.1 Motion Features; 3.5.2 Location Features; 3.6 Sign Level Classification; 3.6.1 Markov Models; 3.6.2 SP Boosting; 3.7 Appearance Based Results; 3.8 2D Tracking Results; 3.9 3D Tracking Results
3.9.1 Data Sets3.9.2 GSL Results; 3.9.3 DGS Results; 3.10 Discussion; 3.11 Conclusions; 3.12 Future Work; References; 4 MAGIC Summoning: Towards Automatic Suggesting and Testing of Gestures with Low Probability of False Positives During Use; 4.1 Introduction; 4.2 MAGIC Summoning Web-Based Toolkit; 4.2.1 Creating Gesture Classes and Testing for Confusion Between Classes; 4.2.2 Android Phone Accelerometer Everyday Gesture Library; 4.2.3 Testing for False Positives with the EGL; 4.3 False Positive Prediction; 4.3.1 Overview of EGL Search Method and Assumptions; 4.3.2 SAX Encoding
2012): One Shot Learning; 1.3.2 ChaLearn Multimodal Gesture Recognition Challenge 2013; 1.3.3 ChaLearn Multimodal Gesture Spotting Challenge 2014
1.3.4 ChaLearn Action and Interaction Spotting Challenge 20141.3.5 ChaLearn Action and Interaction Spotting Challenge 2015; 1.3.6 Other International Competitions for Gesture and Action Recognition; 1.4 Summary of Special Topic Papers Not Related to the Challenges; 1.5 Summary of Special Topic Papers Related to 2011
2012 Challenges; 1.6 Summary of Special Issue Papers Related to 2013 Challenge; 1.7 Discussion; References; 2 Human Gesture Recognition on Product Manifolds; 2.1 Introduction; 2.2 Related Work; 2.3 Mathematical Background ; 2.3.1 Tensor Representation; 2.3.2 Orthogonal Groups
2.3.3 Stiefel Manifolds2.3.4 Grassmann Manifolds; 2.4 Elements of Product Manifolds ; 2.4.1 Product Manifolds; 2.4.2 Factorization in Product Spaces; 2.4.3 Geodesic Distance on Product Manifolds; 2.5 The Product Manifold Representation ; 2.6 Statistical Modeling; 2.6.1 Linear Least Squares Regression; 2.6.2 Least Squares Regression on Manifolds; 2.7 Experimental Results; 2.7.1 Cambridge Hand-Gesture Data Set; 2.7.2 UMD Keck Body-Gesture Data Set; 2.7.3 One-Shot-Learning Gesture Challenge; 2.8 Discussion; 2.9 Conclusions; References; 3 Sign Language Recognition Using Sub-units
3.1 Introduction3.2 Background; 3.2.1 Linguistics; 3.3 Learning Appearance Based Sub-units; 3.3.1 Location Features; 3.3.2 Motion and Hand-Arrangement Moment Feature Vectors; 3.3.3 Motion Binary Patterns and Additive Classifiers; 3.4 2D Tracking Based Sub-units; 3.4.1 Motion Features; 3.4.2 Location Features; 3.4.3 HandShape Features; 3.4.4 HandShape Classifiers; 3.5 3D Tracking Based Sub-units; 3.5.1 Motion Features; 3.5.2 Location Features; 3.6 Sign Level Classification; 3.6.1 Markov Models; 3.6.2 SP Boosting; 3.7 Appearance Based Results; 3.8 2D Tracking Results; 3.9 3D Tracking Results
3.9.1 Data Sets3.9.2 GSL Results; 3.9.3 DGS Results; 3.10 Discussion; 3.11 Conclusions; 3.12 Future Work; References; 4 MAGIC Summoning: Towards Automatic Suggesting and Testing of Gestures with Low Probability of False Positives During Use; 4.1 Introduction; 4.2 MAGIC Summoning Web-Based Toolkit; 4.2.1 Creating Gesture Classes and Testing for Confusion Between Classes; 4.2.2 Android Phone Accelerometer Everyday Gesture Library; 4.2.3 Testing for False Positives with the EGL; 4.3 False Positive Prediction; 4.3.1 Overview of EGL Search Method and Assumptions; 4.3.2 SAX Encoding