Canonical Correlation Analysis of Video Volume Tensors for Action Categorization and Detection

By Tae-Kyun Kim, Roberto Cipolla. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009

315 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/215d8ae94adee4a8e09112e13c371d533411c801

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Informative joints based human action recognition using skeleton contexts (2015, methodology): “Contents lists available at ScienceDirect Signal Processing: Image Communication http://d 0923-59 n Corr E-m journal homepage: www.elsevier.com/locate/image Informative joints based human action recognition using skeleton contexts Min Jiang a,n, Jun Kong a,b, George Bebis c, Hongtao Huo d a Key…”
Structured Time Series Analysis for Human Action Segmentation and Recognition (2014, methodology): “Sequentially optimizing L is actually a fixed-length sliding window process which is also used in [30].”
A survey of multilinear subspace learning for tensor data (2011, methodology): “Besides the MSL algorithms reviewed above, there is also a multilinear extension of the CCA algorithm named as tensor CCA in [80].”
Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives (2017, background): “where wpnq P RIn are canonical vectors, Cnn P RIn In are covariance matrices and C P RI1 I2 IN is an Nth-order data tensor (Kim et al., 2007; Kim and Cipolla, 2009; Luo et al., 2015b).”
Human gesture recognition on product manifolds (2012, methodology): “, 2007), and action classification (Vasilescu, 2002; Kim and Cipolla, 2009).”
Online action recognition using covariance of shape and motion (2014, methodology): “Kim and Cipolla [13] extend the Canonical Correlation Analysis (CCA) to tensors and use it to measure the similarity between two video volumes avoiding an explicit motion estimation.”
Coupled information-theoretic encoding for face photo-sketch recognition (2011, methodology): “It was used in some computer vision applications [34, 13, 25].”
Real-Time Online Action Detection Forests Using Spatio-Temporal Contexts (2016, background): “…opportunities, however come with signiﬁcant challenges not encountered by the classical ofﬂine action recognition approaches [49, 42, 12, 40, 47, 44, 43, 39, 7, 15, 19, 50, 5, 10]: Realistic OAD applications require real-time processing that prevents the use of computationally expensive features.”
EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition (2018, methodology): “Dataset 2007 [3], MSRGesture3D 2012 [5], ASL 1998 [17], their statistics are not provided.”
Low-Rank Tensor Subspace Learning for RGB-D Action Recognition (2016, methodology): “As the tensorial dimension is 20 × 20 × 28 from the HON4D with dimension 11200 (obtained in [9]), here we set 3D dimension in [ 2 , 20 ] .”
Linking Image and Text with 2-Way Nets (2016, background): “CCA plays a crucial role in many computer vision applications including multiview analysis [1], multimodal human behavior analysis [39], action recognition [16], and linking text with images [18].”
Temporal Localization of Actions with Actoms (2013, unknown): “For instance, Kim and Cipolla [29] directly compare videos using Tensor Canonical Correlation Analysis.”