Lune

AAAI2023Top-tier venue

Global Dilated Attention and Target Focusing Network for Robust Tracking

Yun Liang, Qiaoqiao Li, Fumian Long

Abstract

Self Attention has shown the excellent performance in tracking due to its global modeling capability. However, it brings two challenges: First, its global receptive field has less attention on local structure and inter-channel associations, which limits the semantics to distinguish objects and backgrounds; Second, its feature fusion with linear process cannot avoid the interference of non-target semantic objects. To solve the above issues, this paper proposes a robust tracking method named GdaTFT by defining the Global Dilated Attention (GDA) and Target Focusing Network (TFN). The GDA provides a new global semantics modeling approach to enhance the semantic objects while eliminating the background. It is defined via the local focusing module, dilated attention and channel adaption module. Thus, it promotes semantics by focusing local key information, building long-range dependencies and enhancing the semantics of channels. Subsequently, to distinguish the target and non-target objects both with rich semantics, the TFN is proposed to accurately focus the target region. Different from the present feature fusion, it uses the template as the query to build a point-to-point correlation between the template and search region, and finally achieves part-level augmentation of target feature in the search region. Thus, the TFN efficiently augments the target embedding while weakening the non-target objects. Experiments on challenging benchmarks (LaSOT, TrackingNet, GOT-10k, OTB-100) demonstrate that the GdaTFT outperforms many state-of-the-art trackers and achieves leading performance. Code will be available.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Transformer Tracking cites SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
  • Transformer Tracking cites Learning Spatio-Temporal Transformer for Visual Tracking
  • Transformer Tracking cites Learning Discriminative Model Prediction for Tracking
  • High-Performance Discriminative Tracking with Transformers cites Learning Discriminative Model Prediction for Tracking
  • Learning Spatio-Temporal Transformer for Visual Tracking cites SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
  • Learning Spatio-Temporal Transformer for Visual Tracking cites Learning Discriminative Model Prediction for Tracking
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. Learning Discriminative Model Prediction for TrackingGoutam Bhat, Martin Danelljan, Luc Van Gool, Radu TimofteICCV 2019 · 1,294 citations
  2. Learning Spatio-Temporal Transformer for Visual TrackingBin Yan, Houwen Peng, Jianlong Fu, Dong Wang et al.ICCV 2021 · 1,062 citations
  3. SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation GuidelinesYinda Xu, Zeyu Wang, Zuoxin Li, Ye Yuan et al.AAAI 2020 · 944 citations
  4. High-Performance Discriminative Tracking with TransformersBin Yu, Ming Tang, Linyu Zheng, Guibo Zhu et al.ICCV 2021 · 113 citations
  5. Transformer TrackingXin Chen, Bin Yan, Jiawen Zhu, Dong Wang et al.CVPR 2021

Related papers

  1. Graph Attention TrackingDongyan Guo, Yanyan Shao, Ying Cui, Zhenhua Wang et al.CVPR 2021
  2. Target-Aware Tracking with Long-Term Context AttentionKaijie He, Canlong Zhang, Sheng Xie, Zhixin Li et al.AAAI 2023 · 102 citations
  3. Deformable Siamese Attention Networks for Visual Object TrackingYuechen Yu, Yilei Xiong, Weilin Huang, Matthew R. ScottCVPR 2020
  4. MixFormer: End-to-End Tracking with Iterative Mixed AttentionYutao Cui, Cheng Jiang, Limin Wang, Gangshan WuCVPR 2022 · 746 citations
  5. Guided Slot Attention for Unsupervised Video Object SegmentationMinhyeok Lee, Suhwan Cho, Dogyoon Lee, Chaewon Park et al.CVPR 2024
Dusk over the sea between two cliffs drawn in fine vertical lines