Open AccessPosted Content
A Differentiable Recurrent Surface for Asynchronous Event-Based Data
TL;DR: In this paper, a grid of Long Short-Term Memory (LSTM) cells is proposed to learn end-to-end task-dependent event-surfaces, which shows good flexibility and expressiveness on optical flow estimation.
read more
Abstract: Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes. Differently from classic vision devices, they produce a sparse representation of the scene. Therefore, to apply standard computer vision algorithms, events need to be integrated into a frame or event-surface. This is usually attained through hand-crafted grids that reconstruct the frame using ad-hoc heuristics. In this paper, we propose Matrix-LSTM, a grid of Long Short-Term Memory (LSTM) cells that efficiently process events and learn end-to-end task-dependent event-surfaces. Compared to existing reconstruction approaches, our learned event-surface shows good flexibility and expressiveness on optical flow estimation on the MVSEC benchmark and it improves the state-of-the-art of event-based object classification on the N-Cars dataset.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras
Lin Zhu,Jianing Li,Xiao Wang,Tiejun Huang,Yonghong Tian +4 more
- 01 Jan 2021
•Posted Content
Event-LSTM: An Unsupervised and Asynchronous Learning-based Representation for Event-based Data.
TL;DR: In this paper, an unsupervised Auto-Encoder architecture made up of LSTM layers is proposed to learn 2D grid representation from event sequence, which is a task-agnostic approach ideally suited for the event domain.
9
•Posted Content
Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
Giorgio Giannone,Asha Anoosheh,Alessio Quaglino,Pierluca D'Oro,Marco Gallieri,Jonathan Masci +5 more
TL;DR: This work proposes to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates as the input for a novel RNN-like architecture, the Input-filtering Neural ODEs (INODE) that allows for input signals to be continuously fed to the network, like in filtering.
9
Neural Implicit Event Generator for Motion Tracking
23 May 2022
TL;DR: In this paper , the authors present a framework of motion tracking from event data using implicit expression, which uses pre-trained event generation MLP called the implicit event generator (IEG) and carries out motion tracking by updating its state (position and velocity) based on the difference between the observed event and generated event from the current state estimation.
•Posted Content
Neural Implicit Event Generator for Motion Tracking.
TL;DR: In this article, the authors present a framework of motion tracking from event data using implicit expression, which uses pre-trained event generation MLP named implicit event generator (IEG) and does motion tracking by updating its state based on the difference between the observed event and generated event from the current state estimate.
1
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.