Sparse Coding Of Time-Varying Natural Images

By Barbara Olshausen. 2010

56 citations recorded by the source corpus.

We show how the principle of sparse coding may be applied to learn the forms of structure occurring in time-varying natural images. A sequence of images is described as a linear superposition of space-time functions , each of which is convolved with a time-varying coeecient signal. When a sparse, independent representation is sought over the coeecients, the basis functions that emerge are space-time inseparable functions that resemble the motion-selective receptive elds of cortical simple cells. Interestingly, the coeecients form a spike-like representation of moving images, and thus suggest an interpretation of spiking activity in the brain in terms of sparse coding in time.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

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

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

The Challenges of Continuous Self-Supervised Learning (2022, methodology): “coding [36, 54, 55], inpainting [59] and colorization [18, 34, 86], to methods that learn representations predictive of spatial context [19, 22, 53], temporal context [21, 47, 58, 61, 79, 80], or concurrent modalities like audio [4, 52, 57, 70], text [17, 23, 62] or speech [43, 44].”
Audio-Visual Instance Discrimination with Cross-Modal Agreement (2020, methodology): “Self-supervised methods often try to reconstruct the input data or impose constraints on the representation, such as sparsity [48, 59, 60], noise [82] or invariance [8, 10, 11, 17, 28, 35, 53, 69] to learn a useful and transferable feature representation.”
Efficient sparse coding algorithms (2006, methodology): “When a sparse coding algorithm is applied to natural images, the learned bases resemble the receptive fields of neurons in the visual cortex [1, 2]; moreover, sparse coding produces localized bases when applied to other natural stimuli such as speech and video [3, 4].”
Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization (2013, background): “Sparse coding of natural images has yielded dictionary atoms which resemble the receptive fields of neurons in the visual cortex [26, 27] and has also yielded localized dictionary elements on speech and video data [19, 25].”
Online detection of unusual events in videos via dynamic sparse coding (2011, background): “Moreover, sparse coding has been shown to produce localized bases when applied to other natural stimuli such as video and speech [16, 13].”
Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis (2011, unknown): “Experimental studies in this field have shown that these algorithms can learn receptive fields similar to the V1 area of visual cortex when applied to static images and the MT area of visual cortex when applied to sequences of images [10, 40, 32].”