LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning

Documenti analoghi

• Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models
  di: Zhang, Dewen, et al.
  Pubblicazione: (2024)
• PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
  di: Zhang, Dewen, et al.
  Pubblicazione: (2025)
• LLaVA-c: Continual Improved Visual Instruction Tuning
  di: Liu, Wenzhuo, et al.
  Pubblicazione: (2025)
• LLaVA-Video: Video Instruction Tuning With Synthetic Data
  di: Zhang, Yuanhan, et al.
  Pubblicazione: (2024)
• MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
  di: Zhao, Xiangyu, et al.
  Pubblicazione: (2024)