• Home
  • Search
  • A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking
  • Cite Icon5
  • https://doi.org/10.3390/electronics9050854Copy DOI Icon

A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Visual object tracking by Siamese networks has achieved favorable performance in accuracy and speed. However, the features used in Siamese networks have spatially redundant information, which increases computation and limits the discriminative ability of Siamese networks. Addressing this issue, we present a novel frequency-aware feature (FAF) method for robust visual object tracking in complex scenes. Unlike previous works, which select features from different channels or layers, the proposed method factorizes the feature map into multi-frequency and reduces the low-frequency information that is spatially redundant. By reducing the low-frequency map’s resolution, the computation is saved and the receptive field of the layer is also increased to obtain more discriminative information. To further improve the performance of the FAF, we design an innovative data-independent augmentation for object tracking to improve the discriminative ability of tracker, which enhanced linear representation among training samples by convex combinations of the images and tags. Finally, a joint judgment strategy is proposed to adjust the bounding box result that combines intersection-over-union (IoU) and classification scores to improve tracking accuracy. Extensive experiments on 5 challenging benchmarks demonstrate that our FAF method performs favorably against SOTA tracking methods while running around 45 frames per second.

Loading PDF

Similar Papers
  • Research Article
  • Citations8

Adaptive chaotic sampling particle filter to handle occlusion and fast motion in visual object tracking

  • Jan 20, 2023
  • Digital Signal Processing
  • Marjan Firouznia +4
  • Research Article
  • Citations45

Multitarget Tracking Using Siamese Neural Networks

  • May 18, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Na An +1
  • Research Article
  • Citations9

Biogeography based optimization method for robust visual object tracking

  • Apr 11, 2022
  • Applied Soft Computing
  • Seyed Abbas Daneshyar +1
  • Research Article
  • Citations16

STResNet_CF Tracker: The Deep Spatiotemporal Features Learning for Correlation Filter Based Robust Visual Object Tracking

  • Jan 01, 2019
  • IEEE Access
  • Zhengyu Zhu +4
  • Research Article
  • Citations40

Gaussian-response correlation filter for robust visual object tracking

  • Jun 12, 2020
  • Neurocomputing
  • Sathishkumar Moorthy +2
  • Research Article
  • Citations8

Discriminative object tracking with subspace representation

  • Jun 05, 2020
  • The Visual Computer
  • Rajkumari Bidyalakshmi Devi +2
  • Conference Article
  • Citations77

IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

  • Jun 01, 2021
  • Shuai Jia +3
  • Research Article
  • Citations8

Attention shake siamese network with auxiliary relocation branch for visual object tracking

  • Mar 12, 2020
  • Neurocomputing
  • Jun Wang +4
  • Research Article
  • Citations52

Aberrance suppressed spatio-temporal correlation filters for visual object tracking

  • Feb 27, 2021
  • Pattern Recognition
  • Dinesh Elayaperumal +1
  • Supplementary Content
  • Citations1

Learning Enhanced Feature Responses for Visual Object Tracking.

  • Feb 08, 2022
  • Computational Intelligence and Neuroscience
  • Runqing Zhang +2
  • Research Article

Evaluating the impact of dehazing algorithms on object tracking performance

  • Dec 01, 2025
  • Signal, Image and Video Processing
  • H Seckin Demir +4
  • Research Article
  • Citations10

Visual object tracking using sparse context-aware spatio-temporal correlation filter

  • May 01, 2020
  • Journal of Visual Communication and Image Representation
  • Dinesh Elayaperumal +1
  • Book Chapter
  • Citations14

Multiple Context Features in Siamese Networks for Visual Object Tracking

  • Jan 01, 2019
  • Henrique Morimitsu
  • Video Transcripts

Reducing False Positives in Object Tracking With Siamese Network

  • Dec 29, 2020
  • Underline Science Inc.
  • Takuya Ogawa
  • Conference Article
  • Citations1

Reducing False Positives in Object Tracking with Siamese Network

  • Jan 10, 2021
  • Takuya Ogawa +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.