SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding

Documenti analoghi

• VDPP: Video Depth Post-Processing for Speed and Scalability
  di: Yoon, Daewon, et al.
  Pubblicazione: (2026)
• Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset
  di: Zinnen, Mathias, et al.
  Pubblicazione: (2025)
• OpenFusion++: An Open-vocabulary Real-time Scene Understanding System
  di: Jin, Xiaofeng, et al.
  Pubblicazione: (2025)
• Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery
  di: Zhang, Bohan, et al.
  Pubblicazione: (2026)
• Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos
  di: Zhang, Junbin, et al.
  Pubblicazione: (2022)