Prompt learning has attracted broad attention in computer vision since the large pre-trained
vision-language models (VLMs) exploded. Based on the close relationship between vision …

Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional
visual concepts, eg., sliced tomatoes, where the model is learned only from the seen …

Recent approaches have shown that large-scale vision-language models such as CLIP can
improve semantic segmentation performance. These methods typically aim for pixel-level …

Visual scenes are naturally organized in a hierarchy where a coarse semantic is recursively
comprised of several fine details. Exploring such a visual hierarchy is crucial to recognize …

Traditional deep-learning models use pre-trained knowledge on large-scale datasets to fine-
tune the model. This strategy significantly improves the performance of downstream tasks …

Image segmentation is a long-standing challenge in computer vision, studied continuously
over several decades, as evidenced by seminal algorithms such as N-Cut, FCN, and …

Multi-modal Unsupervised Domain Adaptation (MM-UDA) for large-scale 3D semantic
segmentation involves adapting 2D and 3D models to a target domain without labels, which …

The contrastive language-image pretraining (CLIP) model has shown promise in
generalization recognition by combining visual and textual embeddings. However, the …

Recently, large-scale visual language pre-trained (VLP) models have demonstrated
impressive performance across various downstream tasks. Motivated by these …

Multi-task dense prediction plays an important role in the field of computer vision and has an
abundant array of applications. Its main purpose is to reduce the amount of network training …