MFST: Multi-Features Siamese Tracker
Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

TL;DR
MFST introduces a novel multi-feature fusion approach in Siamese tracking, leveraging hierarchical features and multi-CNN models to improve robustness and accuracy over existing methods.
Contribution
The paper proposes a new Siamese tracking algorithm that fuses multiple hierarchical features and uses multi-CNN models for enhanced robustness and performance.
Findings
Outperforms several state-of-the-art trackers.
Achieves higher tracking accuracy.
Utilizes hierarchical feature fusion for robustness.
Abstract
Siamese trackers have recently achieved interesting results due to their balance between accuracy and speed. This success is mainly due to the fact that deep similarity networks were specifically designed to address the image similarity problem. Therefore, they are inherently more appropriate than classical CNNs for the tracking task. However, Siamese trackers rely on the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not the optimal choice within the deep similarity framework, as multiple convolutional layers provide several abstraction levels in characterizing an object. Starting from this motivation, we present the Multi-Features Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Face recognition and analysis · Human Pose and Action Recognition
