Transformer Tracking

by   Xin Chen, et al.

Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region. However, the correlation operation itself is a local linear matching process, leading to lose semantic information and fall into local optimum easily, which may be the bottleneck of designing high-accuracy tracking algorithms. Is there any better feature fusion method than correlation? To address this issue, inspired by Transformer, this work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. Finally, we present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Experiments show that our TransT achieves very promising results on six challenging datasets, especially on large-scale LaSOT, TrackingNet, and GOT-10k benchmarks. Our tracker runs at approximatively 50 fps on GPU. Code and models are available at


page 1

page 5


High-Performance Transformer Tracking

Correlation has a critical role in the tracking field, especially in rec...

TrTr: Visual Tracking with Transformer

Template-based discriminative trackers are currently the dominant tracki...

ABC: Attention with Bilinear Correlation for Infrared Small Target Detection

Infrared small target detection (ISTD) has a wide range of applications ...

SwinTrack: A Simple and Strong Baseline for Transformer Tracking

Transformer has recently demonstrated clear potential in improving visua...

DASTSiam: Spatio-Temporal Fusion and Discriminative Augmentation for Improved Siamese Tracking

Tracking tasks based on deep neural networks have greatly improved with ...

Transformer Lesion Tracker

Evaluating lesion progression and treatment response via longitudinal le...

MixFormerV2: Efficient Fully Transformer Tracking

Transformer-based trackers have achieved strong accuracy on the standard...

Code Repositories


Transformer Tracking (CVPR2021)

view repo

Please sign up or login with your details

Forgot password? Click here to reset