Abstract: Object-based visual-inertial odometry (VIO) is applied broadly in location service for ground vehicles and robotics, but tends to be limited to research of ...
Abstract: The dominant trackers generate a fixed-size rectangular region based on the previous prediction or initial bounding box as the model input, i.e., search region. While this manner obtains ...
To address object hallucination, several Contrastive Decoding strategies have been introduced in recent years. Among these, Visual Contrastive Decoding (VCD) method has shown promise in reducing ...
Memory-based trackers such as SAM2 demonstrate remarkable performance, however still struggle with distractors. We propose a new plug-in distractor-aware memory (DAM) and management strategy that ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results