Action recognition on motion capture data using a dynemes and forward differences representation

By Ioannis Kapsouras, N. Nikolaidis. 2014

75 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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 Control and Systems Engineering

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Bag-of-words encoding is widely employed by a large number of skeleton-based human representations [100], [106], [118], [134], [135], [138], [141], [143], [149], [152], [155], [157], [165], [170], [177], [179],”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “ 11. EXPERIMENTAL RESULTS ON THE BERKELEY MHAD DATASET Method Feature Acc. Oﬂi et al. [89] Geometric 95.4% Vantigodi et al. [90] Geometric 96.1% Vantigodi et al. [91] Geometric 97.6% Kapsouras et al. [92] Geometric 98.2% Hierarchical RNN [30] Geometric 100% Co-occurrence LSTM [48] Geometric 100% ST-”
A novel hierarchical framework for human action recognition (2016, methodology): “[21] further considered the time scale for 34 motion features to fit various movement speeds.”
Skeleton based action recognition with convolutional neural network (2015, result): “In contrast to those handcrafted features based approaches [6, 13, 17, 18], our approach, like [1], is an effective end-to-end solution to skeleton based action recognition.”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, methodology): “Action recognition on motion capture data using a dynemes and forward differences representation, Kapsouras and Nikolaidis [31] 2014 - 93.”
Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks (2018, unknown): “[51] − − − − 98.”
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold (2016, unknown): “58 - - - Dynemes [19] 98.”
Hierarchical recurrent neural network for skeleton based action recognition (2015, result): “[14], and comparable results with Chaudhry et al.”
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition (2017, result): “Besides, comparisons with previous works [18, 23, 7, 5, 14] show that our spatio-temporal weights learning method is able to effectively discover key factors of actions and achieve the best performance.”
Hand Gesture Recognition in Real Time for Automotive Interfaces: A Multimodal Vision-Based Approach and Evaluations (2014, background): “Information of pose, although difficult to obtain in our application , is also highly useful for recognition, as demonstrated in [25]–[30].”