This paper presents ClusterFormer, a universal vision model that is based on the Clustering
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …

Gastric cancer and Colon adenocarcinoma represent widespread and challenging
malignancies with high mortality rates and complex treatment landscapes. In response to the …

We introduce SEA-RAFT, a more simple, efficient, and accurate RAFT for optical flow.
Compared with RAFT, SEA-RAFT is trained with a new loss (mixture of Laplace). It directly …

The task of point cloud segmentation, comprising semantic, instance, and panoptic
segmentation, has been mainly tackled by designing task-specific network architectures …

Breast cancer is a relatively common cancer among gynecological cancers. Its diagnosis
often relies on the pathology of cells in the lesion. The pathological diagnosis of breast …

As the size of transformer-based models continues to grow, fine-tuning these large-scale
pretrained vision models for new tasks has become increasingly parameter-intensive …

Self-supervised space-time correspondence learning utilizing unlabeled videos holds great
potential in computer vision. Most existing methods rely on contrastive learning with mining …

Optical flow estimation a process of predicting pixel-wise displacement between consecutive
frames has commonly been approached as a regression task in the age of deep learning …

Video object segmentation (VOS) plays an important role in video analysis and
understanding, which in turn facilitates a number of diverse applications, including video …

Deepfake technology, utilizing deep learning and computer vision, presents significant
security threats by generating highly realistic synthetic media, such as images and videos. In …