Significant advancements have been witnessed in visual tracking applications leveraging ViT in recent years, mainly due to the formidable modeling capabilities of Vision Transformer (ViT). However, the strong performance of such trackers heavily relies on ViT models pretrained for long periods, limiting more flexible model designs for tracking tasks. To address this issue, we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders, called TrackMAE. During pretraining, we employ two shared-parameter ViTs, serving as the appearance encoder and motion encoder, respectively. The appearance encoder encodes randomly masked image data, while the motion encoder encodes randomly masked pairs of video frames. Subsequently, an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel level. In this way, ViT learns to understand both the appearance of images and the motion between video frames simultaneously. Experimental results demonstrate that ViT-Base and ViT-Large models, pretrained with TrackMAE and combined with a simple tracking head, achieve state-of-the-art (SOTA) performance without additional design. Moreover, compared to the currently popular MAE pretraining methods, TrackMAE consumes only 1/5 of the training time, which will facilitate the customization of diverse models for tracking. For instance, we additionally customize a lightweight ViT-XS, which achieves SOTA efficient tracking performance.

While object tracking has made significantly strides in accuracy, there remains a notable gap in attention toward speed. Most trackers prioritize achieving real-time speed on powerful GPUs, yet practical applications demand higher tracking speeds, particularly on edge platforms. In response to this need, we introduce HCAT, an efficient tracking method designed for high speeds across diverse devices while maintaining superior tracking accuracy. At the core of HCAT lies a hierarchical cross-attention transformer that mitigates the serial nature of the transformer-based tracking model. Additionally, to further enhance the tracker's speed, we propose a feature sparsification module crafted to sparsify template features, consequently reducing the computational load of the model. HCAT demonstrates remarkable speed alongside competitive performance. For instance, it attains 55 fps on the NVIDIA Jetson AGX Xavier edge device, coupled with a 76.6% AUC score on the TrackingNet benchmark. Furthermore, we have developed an enhanced version, HCAT-M, integrating a multi-template framework and an update head. This variant establishes new state-of-the-art performance for high-speed tracking. Code and models are available at https://github.com/chenxin-dlut/HCAT.