From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding

Documenti analoghi

• HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding
  di: Zou, Heqing, et al.
  Pubblicazione: (2025)
• Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
  di: Chen, Ruizhe, et al.
  Pubblicazione: (2025)
• Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
  di: Wang, Wentao, et al.
  Pubblicazione: (2025)
• Text-based Talking Video Editing with Cascaded Conditional Diffusion
  di: Han, Bo, et al.
  Pubblicazione: (2024)
• Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages
  di: Zou, Heqing, et al.
  Pubblicazione: (2025)