1

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
Many Perception Tasks are Highly Redundant Functions of their Input Data
Many Perception Tasks are Highly Redundant Functions of their Input Data
M3ED: Multi-Robot, Multi-Sensor, Multi-Environment Event Dataset
M3ED: Multi-Robot, Multi-Sensor, Multi-Environment Event Dataset
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors
Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors
Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection
Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection
On-device event filtering with binary neural networks for pedestrian detection using neuromorphic vision sensors
On-device event filtering with binary neural networks for pedestrian detection using neuromorphic vision sensors
Reward Prediction Error as an Exploration Objective in Deep RL
Reward Prediction Error as an Exploration Objective in Deep RL
Experimental results of a compressive reflector antenna producing spatial coding