Can I read Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking on EtoBox?

Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking by Marvasti-Zadeh, Seyed Mojtaba; Ghanei-Yakhdan, Hossein; Kasaei, Shohreh is a scholarly article available to read on EtoBox.

What is Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking about?

Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved great success in challenging scenarios for visual tracking purposes. Although many of those trackers utilize the feature maps from pre-trained convolutional neural networks (CNNs), the effects of selecting different models and exploiting various combinations of their feature maps are still not compared completely. To the best of our knowledge, all those methods use a fixed number of convolutional feature maps without considering the scene attributes (e.g., occlusion, deformation, and fast motion) that might occur during tracking. As a pre-requisition, this paper proposes adaptive discriminative correlation filters (DCF) based on the methods that can exploit CNN models with different topologies. First, the paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model. Second, with the aid of analysis results as attribute dictionaries, adaptive exploitation of deep features is proposed to improve the accuracy and robustness of visual trackers regarding video characteristi

Author

Marvasti-Zadeh, Seyed Mojtaba; Ghanei-Yakhdan, Hossein; Kasaei, Shohreh

Published

2020

Language

EN