A high performance computing method for accelerating temporal action proposal generation

06/15/2019
by   Shiye Lei, et al.
0

Temporal action proposal generation, coming from temporal action recognition, is an important and challenging problem in computer vision. Because of the big capacity of video files, the speed of temporal action recognition is difficult for both researchers and companies. To training a convolutional neural network (CNN) for temporal action recognition, a lot of videos are required to put into the CNN. A speed-up for the task should be proposed for the training process to achieve the faster response of temporal action recognition system. To address it, we implement ring parallel architecture by Massage Passing Interface (MPI). Different from traditional parameter server architecture, total data transmission is reduced by adding a connection between multiple computing load in our new architecture. Compared to parameter server architecture, our parallel architecture has higher efficiency on temporal action proposal generation task with multiple GPUs, which is significant to dealing with large-scale video database. And based on the absence of evaluating time consumption in a distributed deep learning system, we proposed a concept of training time metrics which can assess the performance in the distributed training process.

READ FULL TEXT
research
06/15/2019

Improving temporal action proposal generation by using high performance computing

Temporal action proposal generation is an important and challenging prob...
research
06/27/2017

Recurrent Residual Learning for Action Recognition

Action recognition is a fundamental problem in computer vision with a lo...
research
12/15/2021

Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks

Recently, video-based action recognition methods using convolutional neu...
research
06/17/2020

A Real-time Action Representation with Temporal Encoding and Deep Compression

Deep neural networks have achieved remarkable success for video-based ac...
research
09/13/2023

TransNet: A Transfer Learning-Based Network for Human Action Recognition

Human action recognition (HAR) is a high-level and significant research ...
research
05/28/2017

Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks

In many sports, it is useful to analyse video of an athlete in competiti...
research
10/21/2019

Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition

The importance of inference in Machine Learning (ML) has led to an explo...

Please sign up or login with your details

Forgot password? Click here to reset