# SANet: Structure-Aware Network for Visual Tracking

arXiv: https://arxiv.org/abs/1611.06878 · HTML: https://mlsanity.com/paper/1611.06878/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2016.

## Built on by (most cited first, 9 of 9)

- [Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer](https://mlsanity.com/paper/2303.08622/) (2023)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [FOCUS: Fused Observation of Channels for Unveiling Spectra](https://mlsanity.com/paper/2507.14787/) (2025)
- [LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Images](https://mlsanity.com/paper/2503.18294/) (2025)
- [Benchmarking Deep Trackers on Aerial Videos](https://mlsanity.com/paper/2103.12924/) (2021)
- [Single Object Tracking Research: A Survey](https://mlsanity.com/paper/2204.11410/) (2022)
- [Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking](https://mlsanity.com/paper/2107.02984/) (2021)
- [Adaptive Subsampling for ROI-based Visual Tracking: Algorithms and FPGA Implementation](https://mlsanity.com/paper/2112.09775/) (2021)
- [Staged Depthwise Correlation and Feature Fusion for Siamese Object Tracking](https://mlsanity.com/paper/2310.09747/) (2023)

## Abstract (arXiv)

Convolutional neural network (CNN) has drawn increasing interest in visual tracking owing to its powerfulness in feature extraction. Most existing CNN-based trackers treat tracking as a classification problem. However, these trackers are sensitive to similar distractors because their CNN models mainly focus on inter-class classification. To address this problem, we use self-structure information of object to distinguish it from distractors. Specifically, we utilize recurrent neural network (RNN) to model object structure, and incorporate it into CNN to improve its robustness to similar distractors. Considering that convolutional layers in different levels characterize the object from different perspectives, we use multiple RNNs to model object structure in different levels respectively. Extensive experiments on three benchmarks, OTB100, TC-128 and VOT2015, show that the proposed algorithm outperforms other methods. Code is released at http://www.dabi.temple.edu/~hbling/code/SANet/SANet.html.