EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding

Documenti analoghi

• SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding
  di: Han, Jiwook, et al.
  Pubblicazione: (2026)
• DEVIAS: Learning Disentangled Video Representations of Action and Scene
  di: Bae, Kyungho, et al.
  Pubblicazione: (2023)
• PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
  di: Lee, Jongseo, et al.
  Pubblicazione: (2024)
• Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding
  di: Ren, Junlong, et al.
  Pubblicazione: (2025)
• TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding
  di: Lee, Jin-Seop, et al.
  Pubblicazione: (2025)