ECSNet: Spatio-Temporal Feature Learning for Event Camera

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 2; pp. 701 - 712
• Main Authors: Chen, Zhiwen, Wu, Jinjian, Hou, Junhui, Li, Leida, Dong, Weisheng, Shi, Guangming
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: action recognition; Brightness; Cameras; Cloud computing; Data mining; Event camera; Feature extraction; Machine learning; Modules; Moving object recognition; object classification; Representation learning; Representations; Robustness; Sparsity; spatio-temporal feature learning; Task analysis; Weight reduction

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 irregular layout of the event signals, how to leverage their plentiful spatio-temporal information for recognition tasks re...