Abstract: Pre-trained encoders in computer vision have recently received great attention from both research and industry communities. Among others, a promising paradigm is to utilize self-supervised ...

In this work, we introduce DINOv, a Visual In-Context Prompting framework for referring and generic segmentation tasks. For visualization and demos, we also recommend trying T-Rex demo link, which is ...

Abstract: Data-driven fault diagnosis for critical industrial processes has exhibited promising potential with massive operating data from the supervisory control and data acquisition system. However, ...

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...