HIEVT uses an LLM to convert natural language instructions into spatial goals (bounding boxes) and an offline RL policy to track targets to those goals, claiming strong generalization across environments.
Towards distraction-robust active visual tracking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hierarchical Instruction-aware Embodied Visual Tracking
HIEVT uses an LLM to convert natural language instructions into spatial goals (bounding boxes) and an offline RL policy to track targets to those goals, claiming strong generalization across environments.