Deep Learning of Invariant Spatio-Temporal Features from Video

By Bo Chen. 2010

68 citations recorded by the source corpus.

How researchers see this paper

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

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “d for this task. Jhuang et al. [81] used a feedforward hierarchical template matching architecture for action recognition with pre-deﬁned spatio-temporal ﬁlters in the ﬁrst layer. In his thesis, Chen [82] adopted the convolutional RBM (CRBM) as the basic processing unit and proposed the so-called sp”
Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition (2016, background): “Recent work uses Convolutional Neural Networks (CNNs) to address the above challenges [2, 13, 31, 15, 41, 4, 35, 26].”
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.”
TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 ModDrop (2018, unknown): “Spacetime deep belief networks [38] produce high-level representations of video sequences using convolutional RBMs.”
Multi-scale Deep Learning for Gesture Detection and Localization (2014, background): “Space-time deep belief networks [33] produce high-level representations of video sequences using convolutional RBMs.”