Spatiotemporal energy models for the perception of motion.

By Edward H. Adelson, J. Bergen. 1985

Subfields: Computer Vision and Pattern Recognition, Neuroscience

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Neuroscience

Citations in the corpus

Perceiver: General Perception with Iterative Attention (2021, background): “Some attention maps exhibit spatiotemporal structure reminiscent of the ﬁlters seen in spatiotemporal image processing (Adelson & Bergen, 1985; Simoncelli & Heeger, 1998).”
SlowFast Networks for Video Recognition (2018, background): “But what about video signals I(x, y, t)? Motion is the spatiotemporal counterpart of orientation [2], but all spatiotemporal orientations are not equally likely.”
View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, neutral): “This is the same assumption as in the "energy model” of [1].”
How does the brain solve visual object recognition? (2012, neutral): “…have been formalized into the linear-nonlinear (LN) class of encodingmodels inwhicheachneuronadds andsubtract its inputs, followed by a static nonlinearity (e.g., a threshold) to produce a firing rate response (Adelson and Bergen, 1985; Carandini et al., 2005;Heeger et al., 1996;Rosenblatt, 1958).”
A model of neuronal responses in visual area MT. (1998, positive): “In particular, the " motion energy " model accounts for a number of properties of complex cell responses (Pollen & Ronner, 1983; Adelson & Bergen, 1985; Emerson et al., 1992; Heeger, 1992a).”
Learning to Relate Images (2011, methodology): “Like an auto-encoder, this model can be trained with gradient based optimization.”
Optical Flow Estimation Using a Spatial Pyramid Network (2016, methodology): “Burt and Adelson [2] lay out the theory of spatio-temporal models for motion estimation and Heeger [23] provides a computational embodiment.”
A Biologically Inspired System for Action Recognition (2007, methodology): “The energy model was built from two space-time separable filters whose spatial responses are 2D Gabor functions and temporal responses are based on psychophysical experimental results [1, 56].”
Reconstructing visual experiences from brain activity evoked by natural movies (2011, unknown): “Here we present a new motion-energy [10, 11] encoding model that largely overcomes this limitation.”
Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion (2011, background): “nomenon of apparent motion has been investigated in a number of studies that suggest the visual system performs feature matching [90–92] or temporal filtering [93].”
Unsupervised learning of invariant representations (2016, background): “h = 1 corresponds to pooling via sum/average (and is the only pooling function that does not require a nonlinearity); h = 2 corresponds to “energy models” of complex cells (the models have its origin in the observation that receptive fields of adjacent cells are often quadrature pairs and their sum ”
Spatiotemporal elements of macaque v1 receptive fields. (2005, background): “(Adelson and Bergen, 1985).”
Inhibition, spike threshold, and stimulus selectivity in primary visual cortex. (2008, unknown): “Relay cell inputs to different locations within the subfields of simple cells respond with different latencies, creating a spatial gradient of latency across the receptive field in the direction perpendicular to the preferred orientation (Figure 6A) (Adelson and Bergen, 1985; Watson and Ahumada, 198”
Bags of Spacetime Energies for Dynamic Scene Recognition (2014, background): “, as exemplified by stochastic dynamic textures) [1, 29].”