FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering

Documenti analoghi

• 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
  di: Zemskova, Tatiana, et al.
  Pubblicazione: (2024)
• KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM
  di: Nasser, Zaid, et al.
  Pubblicazione: (2025)
• Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph
  di: Linok, Sergey, et al.
  Pubblicazione: (2024)
• SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
  di: Makarov, Vladislav, et al.
  Pubblicazione: (2026)
• HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
  di: Ben-Ami, Dan, et al.
  Pubblicazione: (2026)