Conference item icon

Conference item

Massively parallel video networks

Abstract:

We introduce a class of causal video understanding models that aims to improve efficiency of video processing by maximising throughput, minimising latency, and reducing the number of clock cycles. Leveraging operation pipelining and multi-rate clocks, these models perform a minimal amount of computation (e.g. as few as four convolutional layers) for each frame per timestep to produce an output. The models are still very deep, with dozens of such operations being performed but in a pipelined f...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-01225-0_40
Publication website:
https://link.springer.com/book/10.1007/978-3-030-01225-0
Publisher:
Springer, Cham
Host title:
ECCV 2018: Computer Vision: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IV
Series:
Lecture Notes in Computer Science
Volume:
11208
Pages:
680-697
Publication date:
2018-10-06
Acceptance date:
2018-07-03
Event title:
15th European Conference on Computer Vision (ECCV 2018)
Event location:
Munich, Germany
Event website:
https://eccv2018.org/
Event start date:
2018-09-08
Event end date:
2018-09-14
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
ISBN:
978-3-030-01224-3
Language:
English
Keywords:
Pubs id:
1155874
Local pid:
pubs:1155874
Deposit date:
2021-01-18

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP