A high performance computing method for accelerating temporal action proposal generation

Temporal action recognition always depends on temporal action proposal generation to hypothesize actions. Applications require temporal action proposal generation to handle both large video dataset and generate more potential actions and suffer from high computation cost due to the bottleneck of temporal action proposal generation. To address this, we introduce a ring parallel architecture based on Message Passing Interface, which is a reliable communication protocol and could be supported by multiple programming languages. In our work, total data transmission is reduced by adding a connection between multiple computing load in our new architecture, which is different from the traditional Parameter Server architecture. Remarkably, our parallel architecture outperforms the Parameter Server architecture in the tasks of temporal action proposal generation, especially for large datasets of millions of videos. In addition, a time metric is proposed to evaluate the speed performance in the distributed training process.