VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

Documenti analoghi

• GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
  di: Liao, Ruotong, et al.
  Pubblicazione: (2023)
• METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
  di: Wang, Mengyue, et al.
  Pubblicazione: (2025)
• zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
  di: Ding, Zifeng, et al.
  Pubblicazione: (2023)
• Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
  di: Amoroso, Roberto, et al.
  Pubblicazione: (2024)
• ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
  di: Zhang, Gengyuan, et al.
  Pubblicazione: (2025)