MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation

Documenti analoghi

• GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation
  di: Ding, Henghui, et al.
  Pubblicazione: (2026)
• Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
  di: Ying, Kaining, et al.
  Pubblicazione: (2025)
• MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
  di: Ding, Henghui, et al.
  Pubblicazione: (2025)
• Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
  di: He, Shuting, et al.
  Pubblicazione: (2024)
• MOVE: Motion-Guided Few-Shot Video Object Segmentation
  di: Ying, Kaining, et al.
  Pubblicazione: (2025)