Kernelized covariance for action recognition
Jacopo Cavazza,Andrea Zunino,Marco San Biagio,Vittorio Murino +3 more
- 01 Dec 2016
pp 408-413
48
TL;DR: This paper presents Kernelized-COV, which generalizes the original covariance representation without compromising the efficiency of the computation, and validates the proposed framework against many previous approaches in the literature.
read more
Abstract: 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 trick for computing the covariance matrix, enhancing it to model more complex, non-linear relationships conveyed by the raw data. To this end, we propose Kernelized-COV, which generalizes the original covariance representation without compromising the efficiency of the computation. In the experiments, we validate the proposed framework against many previous approaches in the literature, scoring on par or superior with respect to the state of the art on benchmark datasets for 3D action recognition.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Tensor Representations for Action Recognition.
TL;DR: In this paper, a tensor-based feature representation is proposed to compactly capture higher-order relationships between spatial features and their temporal dynamics in human actions in videos, which can capture the complex interplay between various spatial features.
87
Analyzing human–human interactions: A survey
Alexandros Stergiou,Ronald Poppe +1 more
TL;DR: In this paper, a survey provides a summary of these challenges and datasets to address them, followed by an in-depth discussion of relevant vision-based recognition and detection methods, focusing on recent, promising work based on deep learning and convolutional neural networks (CNNs).
85
A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding
TL;DR: In this article, the authors propose a space-time geometric representation of human landmark configurations and derive tools for comparison and classification, based on the Riemannian geometry of the underlying manifold.
69
•Posted Content
Non-Linear Temporal Subspace Representations for Activity Recognition
TL;DR: A novel pooling method is proposed, kernelized rank pooling, that represents a given sequence compactly as the pre-image of the parameters of a hyperplane in a reproducing kernel Hilbert space, projections of data onto which captures their temporal order.
46
References
Pattern Recognition and Machine Learning
TL;DR: This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
30.8K
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Bernhard Schölkopf,Alexander J. Smola +1 more
- 01 Dec 2001
TL;DR: Learning with Kernels provides an introduction to SVMs and related kernel methods that provide all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms.
10.2K
Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
TL;DR: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond as discussed by the authors The Journal of the American Statistical Association: Vol 98, No 462, pp 489-489
4K
A survey of advances in vision-based human motion capture and analysis
TL;DR: This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.
3K
Related Papers (5)
Wanqing Li,Zhengyou Zhang,Zicheng Liu +2 more
- 13 Jun 2010
Yong Du,Wei Wang,Liang Wang +2 more
- 07 Jun 2015