Human action recognition from various data modalities: A review
Human Action Recognition (HAR) aims to understand human behavior and assign a label to
each action. It has a wide range of applications, and therefore has been attracting increasing …
each action. It has a wide range of applications, and therefore has been attracting increasing …
Graph-based spatio-temporal feature learning for neuromorphic vision sensing
Neuromorphic vision sensing (NVS) devices represent visual information as sequences of
asynchronous discrete events (aka,“spikes”) in response to changes in scene reflectance …
asynchronous discrete events (aka,“spikes”) in response to changes in scene reflectance …
Ecsnet: Spatio-temporal feature learning for event camera
The neuromorphic event cameras can efficiently sense the latent geometric structures and
motion clues of a scene by generating asynchronous and sparse event signals. Due to the …
motion clues of a scene by generating asynchronous and sparse event signals. Due to the …
Globally-optimal contrast maximisation for event cameras
Event cameras are bio-inspired sensors that perform well in challenging illumination
conditions and have high temporal resolution. However, their concept is fundamentally …
conditions and have high temporal resolution. However, their concept is fundamentally …
Spikepoint: An efficient point-based spiking neural network for event cameras action recognition
Event cameras are bio-inspired sensors that respond to local changes in light intensity and
feature low latency, high energy efficiency, and high dynamic range. Meanwhile, Spiking …
feature low latency, high energy efficiency, and high dynamic range. Meanwhile, Spiking …
Event-based gesture recognition with dynamic background suppression using smartphone computational capabilities
In this paper, we introduce a framework for dynamic gesture recognition with background
suppression operating on the output of a moving event-based camera. The system is …
suppression operating on the output of a moving event-based camera. The system is …
Transformer-based domain adaptation for event data classification
Event cameras encode the change of brightness into events, differing from conventional
frame cameras. The novel working principle makes them to have stronger potential in high …
frame cameras. The novel working principle makes them to have stronger potential in high …
Making sense of neuromorphic event data for human action recognition
Neuromorphic vision sensors provide low power sensing and capture salient spatial-
temporal events. The majority of the existing neuromorphic sensing work focus on object …
temporal events. The majority of the existing neuromorphic sensing work focus on object …
VOWEL: A local online learning rule for recurrent networks of probabilistic spiking winner-take-all circuits
H Jang, N Skatchkovsky… - 2020 25th International …, 2021 - ieeexplore.ieee.org
Networks of spiking neurons and Winner-Take-All spiking circuits (WTA-SNNs) can detect
information encoded in spatio-temporal multi-valued events. These are described by the …
information encoded in spatio-temporal multi-valued events. These are described by the …
Accurate depth estimation from a hybrid event-RGB stereo setup
Event-based visual perception is becoming increasingly popular owing to interesting sensor
characteristics enabling the handling of difficult conditions such as highly dynamic motion or …
characteristics enabling the handling of difficult conditions such as highly dynamic motion or …