Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization

Documenti analoghi

• Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
  di: Li, Jiaqi, et al.
  Pubblicazione: (2026)
• A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recovery
  di: Pham, Hoang Hai, et al.
  Pubblicazione: (2026)
• Why Learn What Physics Already Knows? Realizing Agile mmWave-based Human Pose Estimation via Physics-Guided Preprocessing
  di: Zheng, Shuntian, et al.
  Pubblicazione: (2026)
• Masked Diffusion Vision-Language Models for Temporal Action Localization
  di: Wang, Fengshun, et al.
  Pubblicazione: (2026)
• Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
  di: Zhu, Yingjie, et al.
  Pubblicazione: (2025)