arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.09262cs.CVcs.AIcs.NE
收藏

分层注意递归跟踪

Hierarchical Attentive Recurrent Tracking

University of Oxford(牛津大学)

Adam R. Kosiorek, Alex Bewley, Ingmar Posner

摘要:

类不可知的对象跟踪是特别困难的,在杂乱的环境中,因为目标特定的判别模型不能被事先学习。受人类视觉皮层如何利用空间注意力和分离的“哪里”和“什么”处理路径来主动抑制不相关的视觉特征的启发,这项工作开发了一个分层的注意递归模型,用于视频中的单个对象跟踪。第一层注意力通过选择包含感兴趣对象的区域来丢弃大部分背景,而后续层则调整跟踪对象的特定视觉特征。这个框架是完全可区分的,可以通过梯度方法以纯粹的数据驱动方式进行训练。为了提高训练的收敛性,我们增加了损失函数与跟踪相关的一些辅助任务的条款。在两个数据集上对所提出的模型进行评估:KTH活动识别数据集上的行人跟踪和更困难的KITTI对象跟踪数据集。

英文摘要:

Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori. Inspired by how the human visual cortex employs spatial attention and separate "where" and "what" processing pathways to actively suppress irrelevant visual features, this work develops a hierarchical attentive recurrent model for single object tracking in videos. The first layer of attention discards the majority of background by selecting a region containing the object of interest, while the subsequent layers tune in on visual features particular to the tracked object. This framework is fully differentiable and can be trained in a purely data driven fashion by gradient methods. To improve training convergence, we augment the loss function with terms for a number of auxiliary tasks relevant for tracking. Evaluation of the proposed model is performed on two datasets: pedestrian tracking on the KTH activity recognition dataset and the more difficult KITTI object tracking dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑