A
Ashton Fagg
Researcher at Commonwealth Scientific and Industrial Research Organisation
Publications - 8
Citations - 1861
Ashton Fagg is an academic researcher from Commonwealth Scientific and Industrial Research Organisation. The author has contributed to research in topics: Video tracking & Frame rate. The author has an hindex of 4, co-authored 8 publications receiving 1271 citations. Previous affiliations of Ashton Fagg include Queensland University of Technology.
Papers
More filters
Posted Content
Learning Background-Aware Correlation Filters for Visual Tracking
TL;DR: In this article, a background-aware correlation filter is proposed to model how both the foreground and background of the object varies over time, which can be used for real-time tracking.
Proceedings ArticleDOI
Learning Background-Aware Correlation Filters for Visual Tracking
TL;DR: This work proposes a Background-Aware CF based on hand-crafted features (HOG] that can efficiently model how both the foreground and background of the object varies over time, and superior accuracy and real-time performance of the method compared to the state-of-the-art trackers.
Posted Content
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
TL;DR: This paper proposes the first higher frame rate video dataset (called Need for Speed - NfS) and benchmark for visual object tracking and finds that at higher frame rates, simple trackers such as correlation filters outperform complex methods based on deep networks.
Proceedings ArticleDOI
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
TL;DR: The Need for Speed (NfS) dataset as discussed by the authors provides a benchmark for visual object tracking on higher frame rate video sequences and provides an extensive evaluation of many recent and state-of-the-art trackers.
Posted Content
Fast, Dense Feature SDM on an iPhone
TL;DR: In this paper, a sparse compositional regression (SCR) framework is proposed to enable dense SDM to run at over 90 FPS on a mobile device, which enables a significant speed up over classical dense regressors.