Abstract: The detection of traffic objects in aerial scenes holds significant application potential in both military and civilian sectors. However, current aerial traffic object detection techniques ...
Abstract: Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a ...
A comprehensive repository for fine-tuning the Donut model for document image classification and parsing tasks. This project provides optimized training pipelines using Hugging Face Transformers with ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results