The rapid development of deep learning has made a great progress in image segmentation,
one of the fundamental tasks of computer vision. However, the current segmentation …

Semantic segmentation is the pixel-wise labeling of an image. Boosted by the extraordinary
ability of convolutional neural networks (CNN) in creating semantic, high-level and …

Deriving reliable region-word alignment from image-text pairs is critical to learnobject-level
vision-language representations for open-vocabulary object detection. Existing methods …

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled
data to solve complex tasks. While there has been excellent progress with simple, image …

Recently, self-supervised large-scale visual pre-training models have shown great promise
in representing pixel-level semantic relationships, significantly promoting the development …

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping
without human-labeled annotations. With the advent of self-supervised pre-training, various …

Co-occurrent visual pattern makes context aggregation become an essential paradigm for
semantic segmentation. The existing studies focus on modeling the contexts within image …

This work studies the problem of image semantic segmentation. Current approaches focus
mainly on mining “local” context, ie, dependencies between pixels within individual images …

Video shadow detection aims to generate consistent shadow predictions among video
frames. However, the current approaches suffer from inconsistent shadow predictions across …

In this work, we introduce panoramic panoptic segmentation, as the most holistic scene
understanding, both in terms of Field of View (FoV) and image-level understanding for …