Abstract We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation fifilters for increased robustness and computational effificiency. The subset of fifilters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional Correlation Filter Network which allows adaptive tracking of dynamic targets. (ii) Utilising an attentional network which shifts the attention to the best candidate modules, as well as predicting the estimated accuracy of currently inactive modules. (iii) Enlarging the variety of correlation fifilters which cover target drift, blurriness, occlusion, scale changes, and flflexible aspect ratio. (iv) Validating the robustness and effificiency of the attentional mechanism for visual tracking through a number of experiments. Our method achieves similar performance to non real-time trackers, and state-of-the-art performance amongst real-time trackers