Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity

Ähnliche Einträge

• Pose Matters: Evaluating Vision Transformers and CNNs for Human Action Recognition on Small COCO Subsets
  von: Tang, MingZe, et al.
  Veröffentlicht: (2025)
• Navigating Data Scarcity using Foundation Models: A Benchmark of Few-Shot and Zero-Shot Learning Approaches in Medical Imaging
  von: Woerner, Stefano, et al.
  Veröffentlicht: (2024)
• No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning
  von: Todescato, Matheus Vinícius, et al.
  Veröffentlicht: (2025)
• LLM meets Vision-Language Models for Zero-Shot One-Class Classification
  von: Bendou, Yassir, et al.
  Veröffentlicht: (2024)
• Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarization
  von: Wu, Yuanli, et al.
  Veröffentlicht: (2025)