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.
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 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
