Recently integrating video foundation models and large language models to build a video
understanding system can overcome the limitations of specific pre-defined vision tasks. Yet …

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 …

Reference features from a template or historical frames are crucial for visual object tracking.
Prior works utilize all features from a fixed template or memory for visual object tracking …

Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect,
segment, and track arbitrary object categories in a video, without being constrained to …

Recently, integrating video foundation models and large language models to build a video
understanding system can overcome the limitations of specific pre-defined vision tasks. Yet …

Video data refers to digital information in the form of a series of frames or images
representing continuous motion captured by a video recording device. In various domains …

Image-text retrieval is a fundamental task in bridging the semantics between vision and
language. The key challenge lies in accurately and efficiently learning the semantic …

The dominant trackers generate a fixed-size rectangular region based on the previous
prediction or initial bounding box as the model input, ie, search region. While this manner …

In the realm of unmanned aerial vehicle (UAV) tracking, Siamese-based approaches have
gained traction due to their optimal balance between efficiency and precision. However …

Re-detection is a necessary capability for long-term tracking. Target candidate proposals in
the whole image can provide a chance of tracking reset when tracking fails due to tracking …