OVFormer+: Improved Open-Vocabulary Video Instance Segmentation via Text-Guided Unified Embedding Alignment

Hao Fang 0010, Xiankai Lu, Henghui Ding, Yunchao Wei, Yawei Li 0001, Runmin Cong. OVFormer+: Improved Open-Vocabulary Video Instance Segmentation via Text-Guided Unified Embedding Alignment. International Journal of Computer Vision, 134(6):274, June 2026. [doi]

Abstract

Abstract is missing.