Open access
2026
ConsistVIS: A Consistency-Aware Weakly Supervised Video Instance Segmentation Method
Video Instance Segmentation (VIS) is a growing computer vision task that involves segmenting, categorizing, and tracking object instances across video frames. Traditional methods rely on fully-supervised training and computationally intensive transformer models, which are costly and limited by labeling requirements. To...
Farnoosh Arefi, Amir M. Mansourian, A. Babaei et al.
· IEEE Access · 0 citations