Adaptive Feature Representation for Visual Tracking

by   Yuqi Han, et al.

Robust feature representation plays significant role in visual tracking. However, it remains a challenging issue, since many factors may affect the experimental performance. The existing method which combine different features by setting them equally with the fixed weight could hardly solve the issues, due to the different statistical properties of different features across various of scenarios and attributes. In this paper, by exploiting the internal relationship among these features, we develop a robust method to construct a more stable feature representation. More specifically, we utilize a co-training paradigm to formulate the intrinsic complementary information of multi-feature template into the efficient correlation filter framework. We test our approach on challenging se- quences with illumination variation, scale variation, deformation etc. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods favorably.



page 4


What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?

Previous work has shown that feature maps of deep convolutional neural n...

Exploiting Structure Sparsity for Covariance-based Visual Representation

The past few years have witnessed increasing research interest on covari...

Discriminative Feature Representation with Spatio-temporal Cues for Vehicle Re-identification

Vehicle re-identification (re-ID) aims to discover and match the target ...

An efficient real-time target tracking algorithm using adaptive feature fusion

Visual-based target tracking is easily influenced by multiple factors, s...

Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling

It remains a huge challenge to design effective and efficient trackers u...

DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation

While deep learning demonstrates its strong ability to handle independen...

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

Jointly exploiting multiple different yet complementary domain informati...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.