3 papers
cs.CV2025
Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph
Sergey Linok, Gleb Naumov
We propose OVIGo-3DHSG method - Open-Vocabulary Indoor Grounding of objects using 3D Hierarchical Scene Graph. OVIGo-3DHSG represents an extensive indoor environment over a Hierarc…
cs.CV2025
DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes
Sergey Linok, Vadim Semenov, Anastasia Trunova +2
The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approac…
cs.CV2025
Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph
Sergey Linok, Tatiana Zemskova, Svetlana Ladanova +4
Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object gr…