TLG achieves 71.37% accuracy on the TimeLogic Challenge by reconstructing action timelines from source annotations and executing parsed temporal logic programs, with VLM fallback and targeted routing, outperforming baselines by 24.5 points.
arXiv:2509.18041, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TLG: Temporal-Logic Grounding for Video Question Answering via Source-Annotation Reconstruction and Category-Targeted Reasoning
TLG achieves 71.37% accuracy on the TimeLogic Challenge by reconstructing action timelines from source annotations and executing parsed temporal logic programs, with VLM fallback and targeted routing, outperforming baselines by 24.5 points.