HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition

By Xavier Lagorce, Garrick Orchard, Francesco Galluppi, Bertram E. Shi, Ryad Benosman. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017

656 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/73ade9124ef6935e1b9b17243a48fa5320737f94

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

Learning to Detect Objects with a 1 Megapixel Event Camera (2020, methodology): “Here we compare the commonly used Histograms of events [48, 22], Time Surfaces [49], and Event Volumes [23].”
Event-Based Vision: A Survey (2019, methodology): “More recent work obtains features by unsupervised learning, clustering the event data and using the center of each cluster as a feature [93].”
EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras (2018, methodology): “[10] and the ”timestamp images” used in Park et al.”
A Scalable Multicore Architecture With Heterogeneous Memory Structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs) (2017, background): “Furthermore, there are growing efforts towards the direct use of asynchronous event-based data produced by spiking sensors such as the DVS [37]–[42].”
Deep Learning With Spiking Neurons: Opportunities and Challenges (2018, methodology): “In order to tune the trade-oﬀ between rate-based and temporal coding Lagorce et al. (2017) and Sironi et al. (2018) propose to use time surfaces around event input as hierarchical features.”
ESIM: an Open Event Camera Simulator (2018, methodology): “The events are visualized using an exponential time surface [27] with exponential decay τc = 3.”
Direct Training for Spiking Neural Networks: Faster, Larger, Better (2018, background): “Different from the previous spatial back-propagation (Lee, Delbruck, and Pfeiffer 2016; Jin, Li, and Zhang 2018), (Wu et al. 2018) proposed the ﬁrst backpropagation in both spatial and temporal domains to direct train SNNs, which achieved state-of-the-art accuracy on MNIST and N-MNIST datasets.”
High Speed and High Dynamic Range Video with an Event Camera (2019, background): “intermediate, “image-like” representations from event data [13], [14], [15], [15], [16].”