Peripheral visual information dominates human decision making in Atari games, producing the largest accuracy drops (35-44%) when removed from action-prediction models.
Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Estimating Central, Peripheral, and Temporal Visual Contributions to Human Decision Making in Atari Games
Peripheral visual information dominates human decision making in Atari games, producing the largest accuracy drops (35-44%) when removed from action-prediction models.