With the urgent demand for generalized deep models, many pre-trained big models are
proposed, such as bidirectional encoder representations (BERT), vision transformer (ViT) …

In this paper, we present a new sequence-to-sequence learning framework for visual
tracking, dubbed SeqTrack. It casts visual tracking as a sequence generation problem …

We present ARTrack, an autoregressive framework for visual object tracking. ARTrack
tackles tracking as a coordinate sequence interpretation task that estimates object …

All instance perception tasks aim at finding certain objects specified by some queries such
as category names, language expressions, and target annotations, but this complete field …

The current popular two-stream, two-stage tracking framework extracts the template and the
search region features separately and then performs relation modeling, thus the extracted …

Visual object tracking aims to localize the target object of each frame based on its initial
appearance in the first frame. Depending on the input modility tracking tasks can be divided …

In this paper, we study masked autoencoder (MAE) pretraining on videos for matching-
based downstream tasks, including visual object tracking (VOT) and video object …

Recently Transformer has been largely explored in tracking and shown state-of-the-art
(SOTA) performance. However, existing efforts mainly focus on fusing and enhancing …

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive
biases has recently drawn extensive interest. However, existing tracking approaches rely on …

The rich spatio-temporal information is crucial to capture the complicated target appearance
variations in visual tracking. However most top-performing tracking algorithms rely on many …