Single object tracking (SOT) in satellite video (SV) enables the continuous acquisition of
position and range information of an arbitrary object, showing promising value in remote …

Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic
groups from an open set of categories. Most existing methods explore utilizing pre-trained …

Abstract Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models,
we propose LoRAT, a method that unveils the power of larger Vision Transformers (ViT) for …

The core of video understanding tasks such as recognition captioning and tracking is to
automatically detect objects or actions in a video and analyze their temporal evolution …

Visual tracking has made significant improvements in the past few decades. Most existing
state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking …

Existing Siamese or transformer trackers commonly pose visual object tracking as a one-
shot detection problem ie locating the target object in a single forward evaluation scheme …

Current 6D pose estimation methods focus on handling objects that are previously trained,
which limits their applications in real dynamic world. To this end, we propose a geometry …

We present ARTrackV2 which integrates two pivotal aspects of tracking: determining where
to look (localization) and how to describe (appearance analysis) the target object across …

Abstract Multimodal Visual Object Tracking (VOT) has recently gained significant attention
due to its robustness. Early research focused on fully fine-tuning RGB-based trackers which …

Online contextual reasoning and association across consecutive video frames are critical to
perceive instances in visual tracking. However, most current top-performing trackers …