Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis

By Quoc V. Le, Will Y. Zou, Serena Yeung, Andrew Y. Ng. 2011

1,119 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, background): “Such models have been able to perform better than traditional hand-engineered representations in many domains, especially those where good features have not already been engineered (Le et al., 2011).”
Scattering Networks for Hybrid Representation Learning (2018, background): “However, several works indicate that this is not a generic enough representation on top of which to build further modules [6], [31].”
Representation Learning: A Review and New Perspectives (2012, methodology): “Similarly, Le et al. (2011b) recently showed that adding a regularization term of the form ∑ t ∑ j s3(Wjx (t)) to a linear auto-encoder with tied weights, where s3 is a nonlinear convex function, yields an efficient algorithm for learning linear ICA.”
Two-Stream Convolutional Networks for Action Recognition in Videos (2014, methodology): “In [4, 18, 25], a convolutional RBM and ISA were used for unsupervised learning of spatio-temporal features, which were then plugged into a discriminative model for action classification.”
Learning to See by Moving (2015, background): “This hypothesis inspired research in fully unsupervised learning from visual imagery and led to popular algorithms such as ICA [5, 20], autoencoders [24, 9], sparse coding [32], restricted boltzmann machines [27, 37] and others [6].”
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2014, background): “Recently, these deep architectures have demonstrated impressive, state-of-the-art, and sometimes human-competitive results on many pattern recognition tasks, especially vision classification problems [16, 7, 31, 17].”
Unsupervised Learning of Video Representations using LSTMs (2015, methodology): “Le et al. (2011) approached this problem using multiple layers of Independent Subspace Analysis modules.”
Unsupervised Learning of Visual Representations Using Videos (2015, background): “Therefore, researchers have started focusing on learning feature representations using videos [11, 53, 27, 43, 56, 16, 48, 34, 45].”
Spatiotemporal Residual Networks for Video Action Recognition (2016, methodology): “Unsupervised learning techniques have been applied by stacking ISA or convolutional gated RBMs to learn spatiotemporal features for action recognition [16, 25].”
Robust Physical-World Attacks on Deep Learning Models (2017, background): “ing vehicle (ﬁeld test) for the target classiﬁer. 1. Introduction Deep Neural Networks (DNNs) have achieved state-ofthe-art, and sometimes human-competitive, performance on many computer vision tasks [11, 14, 36]. Based on These authors contributed equally. these successes, they are increasingly bei”
Explaining nonlinear classification decisions with deep Taylor decomposition (2015, background): “research fields such as natural language processing [13, 14], human action recognition [15, 16, 17], or physics [18, 19].”
Universal Adversarial Perturbations (2016, background): “Despite the impressive performance of deep neural network architectures on challenging visual classiﬁcation benchmarks [6, 9, 21, 10], these classiﬁers were shown to be highly vulnerable to perturbations.”
Video Action Recognition Via Neural Architecture Searching (2019, background): “Video action recognition [1], which is a hot topic of video analysis and understanding, has drawn considerable attention from both academia and industry, since it has great value to many potential applications, like behaviour analysis [2], security, and video affective computing [3].”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “The resulting representation is then put together with the holistic multimodal features of video sample, to build the input for the holistic DSSCA network (DSSCA ), similar to [27].”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Among a large number of human representation approaches [24], [25], [26], [27], [28], [29], most of the existing 3D based methods can be broadly grouped into two categories: representations based on local features [30], [31] and skeletonbased representations [32] [33] [34].”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “[70] presented an extension of the independent subspace analysis algorithm [128] to learn invariant spatio-temporal features from unlabeled video data.”
C3D: Generic Features for Video Analysis (2014, methodology): “Deep learning has also been applied to video feature learning in an unsuperivsed setting [5, 32].”