Introduces a structured framework showing that visual predicate failures under degradation are non-uniform, with static predicates more robust than dynamic ones like grasp and release, and quantifies downstream accuracy drops.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
eSEC-LAM converts enriched Semantic Event Chains into symbolic states via foundation-model perception and deterministic predicate extraction, yielding competitive action recognition, improved next-primitive prediction, and greater robustness than pure symbolic or end-to-end baselines on EPIC-KITCHEN
citing papers explorer
-
Neuro-Symbolic Manipulation Understanding with Enriched Semantic Event Chains
eSEC-LAM converts enriched Semantic Event Chains into symbolic states via foundation-model perception and deterministic predicate extraction, yielding competitive action recognition, improved next-primitive prediction, and greater robustness than pure symbolic or end-to-end baselines on EPIC-KITCHEN