A VQA model that combines free-energy-inspired frame restoration with a scan-and-gaze prediction head reports competitive results on five benchmarks, though the claimed state-of-the-art performance is not uniformly supported.
The konstanz natural video database (konvid-1k),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment
A VQA model that combines free-energy-inspired frame restoration with a scan-and-gaze prediction head reports competitive results on five benchmarks, though the claimed state-of-the-art performance is not uniformly supported.