---
title: "Joint Neural Architecture Search and Token Pruning for Efficient Visual Tracking"
authors:
  - "Yihong Chen"
  - "Shuo Wang"
  - "Jiayao Zheng"
  - "Yongqiang Bai"
doi: "10.24963/ijcai.2026/113"
url: "https://ijcai.org/proceedings/2026/113"
pdf: "https://ijcai.org/proceedings/2026/0113.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1007-1015"
track: "Main Track"
keywords:
  - "Computer Vision: Motion and tracking"
  - "Computer Vision: Efficiency and Optimization"
---

# Joint Neural Architecture Search and Token Pruning for Efficient Visual Tracking

Yihong Chen, Shuo Wang, Jiayao Zheng, Yongqiang Bai

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1007-1015. DOI: [10.24963/ijcai.2026/113](https://doi.org/10.24963/ijcai.2026/113)

## Abstract

Recently, transformer-based trackers have become the leading approach, surpassing traditional CNN-based trackers in accuracy. However, their high computational demands hinder their deployment on edge platforms, necessitating efficient solutions. To address this, we propose a novel Neural Architecture Search (NAS) framework designed for transformer-based trackers, named NASTrack. This framework incorporates token pruning to optimize both transformer block structures and the layer-wise token keeping ratio, striking a balance between performance and efficiency. To handle the larger search space introduced by the keeping ratio, we propose a blacklist strategy and a matching-based distillation driven by the Token Overlap Ratio (TOR). Our method discovers hundreds of high-performing trackers, with FLOPs ranging from 1G to 18G. The searched trackers consistently outperform existing efficient state-of-the-art trackers such as CompressTracker and LiteTrack under comparable computational budgets.The code and models are available at https://github.com/Cyhoon84/NASTrack.git.