Related papers: When Kernel Methods meet Feature Learning: Log-Cov…
Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown…
Video-based human action recognition is currently one of the most active research areas in computer vision. Various research studies indicate that the performance of action recognition is highly dependent on the type of features being…
3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art…
An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…
Deep learning is ubiquitous across many areas areas of computer vision. It often requires large scale datasets for training before being fine-tuned on small-to-medium scale problems. Activity, or, in other words, action recognition, is one…
Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. However, even the 3D skeletons captured in practice are still…
Deep learning techniques are being used in skeleton based action recognition tasks and outstanding performance has been reported. Compared with RNN based methods which tend to overemphasize temporal information, CNN-based approaches can…
Feature learning in neural networks is crucial for their expressive power and inductive biases, motivating various theoretical approaches. Some approaches describe network behavior after training through a change in kernel scale from…
Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification. However, the use of kernel methods for node classification, which is a related problem to graph representation learning, is…
Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action…
It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods are based on Recurrent Neural Networks which present…
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features,…
Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in non-linear space. Existing works mainly leverage on the…
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and…
Recent methods based on 3D skeleton data have achieved outstanding performance due to its conciseness, robustness, and view-independent representation. With the development of deep learning, Convolutional Neural Networks (CNN) and Long…
In this paper we aim at increasing the descriptive power of the covariance matrix, limited in capturing linear mutual dependencies between variables only. We present a rigorous and principled mathematical pipeline to recover the kernel…
Skeleton based action recognition distinguishes human actions using the trajectories of skeleton joints, which provide a very good representation for describing actions. Considering that recurrent neural networks (RNNs) with Long Short-Term…
Action recognition with 3D skeleton sequences is becoming popular due to its speed and robustness. The recently proposed Convolutional Neural Networks (CNN) based methods have shown good performance in learning spatio-temporal…
Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data. However, these methods rely on human expertise and entail the time-consuming processes of data and…
Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously…