tue-mps/PMT_Video
Updated
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders
VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
models 58
tue-mps/VidEoMT
Updated • 1
tue-mps/towards-video-image-frozen
Updated • 1
tue-mps/coco_panoptic_pmt_large_640_dinov3
Image Segmentation • 53.9M • Updated
tue-mps/coco_panoptic_pmt_small_640_dinov3
Image Segmentation • 7.7M • Updated
tue-mps/coco_panoptic_pmt_base_640_dinov3
Image Segmentation • 30.4M • Updated
tue-mps/ade20k_semantic_pmt_large_512_dinov3
Image Segmentation • Updated
tue-mps/coco_instance_pmt_large_640_dinov3
Image Segmentation • Updated
tue-mps/coco_panoptic_pmt_large_1280_dinov3
Image Segmentation • Updated
tue-mps/coco_instance_pmt_large_1280_dinov3
Image Segmentation • Updated
datasets 0
None public yet