Learning Sparse Representations for Human Action Recognition

By Tanaya Guha, Rabab Kreidieh Ward. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

362 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d88413574ded46e4d90f1f214d1b16669abdf6c4

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-task Sparse Learning with Beta Process Prior for Action Recognition (2013, background): “In [6], the local spatiotemporal descriptor is represented as some linear combination of few dictionary elements via sparse representation instead of the traditional bag-of-features methods that involve clustering and vector quantization.”
Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification (2014, background): “…et al. 2009; Ramirez et al. 2010; Yang et al. 2010b; Rodriguez and Sapiro 2007; Mairal et al. 2012), natural image classification (Rodriguez and Sapiro 2007; Yang et al. 2009), and human action recognition (Qiu et al. 2011; Guha and Ward 2012; Wang et al. 2012; Castrodad and Sapiro 2012), etc.”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, background): “poses in the literature [8], [32], [37], [40], [45], [57].”
Online human gesture recognition from motion data streams (2013, neutral): “We set G = [5, 10, 15, 20] respectively when λ = 100 and β = −0.”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “Local patches, thus, generated are characterized by motion patterns [60], [107], optical flow [73], [123], etc.”
Discriminant Bag of Words based representation for human action recognition (2014, methodology): “Recently, several action descriptors aiming at action recognition in unconstrained environments have been proposed, including local sparse and dense space-time features ([23, 45, 10, 20, 34, 35]).”
Going deeper into action recognition: A survey (2016, methodology): “Interested reader is referred to the work of Harandi et al. (2014); Vemulapalli et al. (2014); Koniusz et al. (2016); Rahmani and Mian (2015) for the MoCap data and Oreifej and Liu (2013); Du et al.”
Coding Kendall's Shape Trajectories for 3D Action Recognition (2018, methodology): “To this end, we propose to build class-specific dictionaries, similarly to [15].”
One-shot learning gesture recognition from RGB-D data using bag of features (2013, background): “The theory of sparse coding and the codebook learning are in a developing stage and the problems for selecting optimal parameters (e.g., γ, sparsity k) are still open issues (Guha and Ward, 2012).”