Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks

Documenti analoghi

• Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection
  di: Wang, Chaoqun, et al.
  Pubblicazione: (2025)
• Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
  di: Han, Chaolei, et al.
  Pubblicazione: (2025)
• STSA: Spatial-Temporal Semantic Alignment for Visual Dubbing
  di: Ding, Zijun, et al.
  Pubblicazione: (2025)
• FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
  di: Yang, Shuai, et al.
  Pubblicazione: (2024)
• Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization
  di: Deng, Hanqiu, et al.
  Pubblicazione: (2023)