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 fashion that enables depth-parallel computation. We illustrate the proposed principles by applying them to existing image architectures and analyse their behaviour on two video tasks: action recognition and human keypoint localisation. The results show that a significant degree of parallelism, and implicitly speedup, can be achieved with little loss in performance.
@article{arxiv.1806.03863,
title = {Massively Parallel Video Networks},
author = {Joao Carreira and Viorica Patraucean and Laurent Mazare and Andrew Zisserman and Simon Osindero},
journal= {arXiv preprint arXiv:1806.03863},
year = {2018}
}
Comments
Fixed typos in densenet model definition in appendix