2 papers
cs.AI2025
GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering
Muhammad Qasim Ali, Saeejith Nair, Alexander Wong +2
Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their hi…
cs.CV2025
SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos
Joshua Li, Fernando Jose Pena Cantu, Emily Yu +3
Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene gra…