Tensor Canonical Correlation Analysis for Action Classification

By Tae-Kyun Kim, Shu-Fai Wong, Roberto Cipolla. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

364 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/baac4ebffdc5955cd5a8a5cf15dfab098c7d0704

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

Citations in the corpus

Human-Computer Interaction. Advanced Interaction Modalities and Techniques (2014, background): “The classification of Signoret and North cited in [33] considers the two distinct functional levels in gestures after a study on people having apraxia problems,”
Recent methods and databases in vision-based hand gesture recognition: A review (2015, methodology): “It has sequences of static images corresponding to hand motions, making it suitable for testing dynamic hand gesture recognition algorithms [137].”
Deep Canonical Correlation Analysis (2013, background): “, 2011), speech processing (Choukri & Chollet, 1986; Rudzicz, 2010; Arora & Livescu, 2013), computer vision (Kim et al., 2007), and multimodal signal processing (Sargin et al.”
Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning (2010, neutral): “We achieved better recognition accuracy than all methods [9], [10], [5], [37], [43] except [42].”
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).”
Video-Based Human Behavior Understanding: A Survey (2013, background): “900 image sequences of nine gesture classes defined by three primitive hand shapes and three primitive motions are presented in [146].”
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, background): “For example, in [9], spatio-temporal third-order tensors on videos is proposed for action analysis, non-negative tensor factorization is used for image denoising in [21], tensor textures are proposed for texture rendering in [26], and higher order tensors are used for face recognition in [25].”
Machine Recognition of Human Activities: A Survey (2008, background): “Recently, Kim et al [65] extended canonical correlation analysis to tensors t match videos directly to templates.”
Deep multi-view learning methods: A review (2021, methodology): “CCA that it usually is utilized to conduct the task of MVL and has obtained promising performance in various tasks including dimension reduction [12, 13, 14], classification [92, 93] and clustering [94, 95], when multiple views are 295 available.”
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests (2010, background): “[5, 8, 9, 27]) have reported satisfactory accuracies on standard human action data sets.”
Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, background): “A popular pixel-based abstraction is the organization of low-level input into vectors in an N-dimensional metric space [26, 27, 25, 28, 23, 29, 30].”
LaRED: a large RGB-D extensible hand gesture dataset (2014, background): “Therefore, another dataset with dynamic gestures is presented in [3] where, 9 dynamic gestures composed by the combination of three primitive shapes and three primitive motions are recorded by two subjects under different illumination conditions.”
Canonical Correlation Analysis of Video Volume Tensors for Action Categorization and Detection (2009, background): “Keywords– Action categorization, gesture recognition, canonical correlation analysis, tensor, action detection, incremental subspace learning, spatiotemporal pattern classification.”
Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification (2010, neutral): “[29] 95%”
A Survey of Datasets for Human Gesture Recognition (2014, background): “CHGD [33] (Cambridge Hand Gesture Dataset) H TV Si.”