基于隐任务学习的动作识别方法

提出一种基于多分类隐任务学习的动作识别方法.将多个动作共享的一组子动作作为隐任务，通过对隐任务的联合学习来建模动作之间的关联，从而训练动作分类器并对视频中人的动作进行识别.利用基于softmax的多分类模型学习多个动作之间的隐任务，能够有效防止动作识别过程中的二义性，同时计算简单，节省了模型训练时间.在UCF sports和Olympic sports数据集上的实验结果表明，本文提出的多分类隐任务学习方法在迭代一次的时间上从130 s缩短至0.5 s，并且能更有效地识别视频中的动作. 

Action Recognition Based on Latent Task Learning

In this paper, a novel approach based on latent task learning was presented for action recognition. A set of sub-actions shared by different actions were taken as the latent task, and then the latent task were jointly learned to model the intrinsic relationship among multiple actions for classifier training and the action recognition of video person. Specifically, a softmax based multi-class model was introduced to learn the latent tasks to avoid the ambiguity during recognition process and save the training time owing to its simple computation. Experimental results on UCF sports and Olympic sports datasets show that, compared with the binary-class based multi-task method the proposed method not only saves the running time from 130 s per iteration to 0.5 s per iteration, but also achieves better performance on action recognition tasks.