Hierarchical attentive recurrent tracking

Conference item

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 of increasing difficulty: pedestrian tracking on the KTH activity recognition dataset and the KITTI object tracking dataset.

Authors: Kosiorek, A; Bewley, A; Posner, H

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Neural Information Processing Systems
• Host title: 30th Neural Information Processing Systems (NIPS 2017)
• Journal: 30th Conference on Neural Information Processing Systems (NIPS 2017)
• Publication date: 2018-07-01
• Acceptance date: 2017-09-04