article2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Jun 1, 2022Closed access

MixFormer: End-to-End Tracking with Iterative Mixed Attention

YCYutao CuiCJCheng JiangLWLimin WangGWGangshan Wu

Nanjing University

Indexed incrossref

Abstract

Tracking often uses a multistage pipeline of feature extraction, target information integration, and bounding box estimation. To simplify this pipeline and unify the process of feature extraction and target information integration, we present a compact tracking framework, termed as MixFormer, built upon transformers. Our core design is to utilize the flexibility of attention operations, and propose a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration. This synchronous modeling scheme allows to extract target-specific discriminative features and perform extensive communication between target and search area. Based on MAM, we build our MixFormer tracking framework…

Citation impact

753
total citations
FWCI
41.36
Percentile
100%
References
79
Citations per year

Authors

4

Topics & keywords

Topics
Keywords
  • Computer science
  • Feature extraction
  • Discriminative model
  • Pipeline (software)
  • Minimum bounding box
  • Artificial intelligence
  • Pattern recognition (psychology)
  • Data mining
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding