UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Neuromorphic Vision Sensing for CNN-based Action Recognition

Chadha, A; Bi, Y; Abbas, A; Andreopoulos, Y; (2019) Neuromorphic Vision Sensing for CNN-based Action Recognition. In: Proceedings of ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp. pp. 7968-7972). IEEE: Brighton, UK. Green open access

[thumbnail of Andreopoulos_nvs_distill_v3.pdf]
Preview
Text
Andreopoulos_nvs_distill_v3.pdf - Accepted Version

Download (574kB) | Preview

Abstract

Neuromorphic vision sensing (NVS) hardware is now gaining traction as a low-power/high-speed visual sensing technology that circumvents the limitations of conventional active pixel sensing (APS) cameras. While object detection and tracking models have been investigated in conjunction with NVS, there is currently little work on NVS for higher-level semantic tasks, such as action recognition. Contrary to recent work that considers homogeneous transfer between flow domains (optical flow to motion vectors), we propose to embed an NVS emulator into a multi-modal transfer learning framework that carries out heterogeneous transfer from optical flow to NVS. The potential of our framework is showcased by the fact that, for the first time, our NVS-based results achieve comparable action recognition performance to motion-vector or optical-flow based methods (i.e., accuracy on UCF-101 within 8.8% of I3D with optical flow), with the NVS emulator and NVS camera hardware offering 3 to 6 orders of magnitude faster frame generation (respectively) compared to standard Brox optical flow. Beyond this significant advantage, our CNN processing is found to have the lowest total GFLOP count against all competing methods (up to 7.7 times complexity saving compared to I3D with optical flow).

Type: Proceedings paper
Title: Neuromorphic Vision Sensing for CNN-based Action Recognition
Event: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Location: Brighton, ENGLAND
Dates: 12 May 2019 - 17 May 2019
ISBN-13: 978-1-4799-8131-1
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICASSP.2019.8683606
Publisher version: https://doi.org/10.1109/ICASSP.2019.8683606
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: neuromorphic vision sensing, transfer learning, knowledge distillation
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10094129
Downloads since deposit
316Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item