Motion-Dependent Object Perception Reveals Limits of Current Video Neural Networks
Matteo Dunnhofer, Jean de Dieu Uwisengeyimana, Kohitij Kar
The paper evaluates how motion affects object perception in artificial vision systems and finds that video-based models can replicate human motion-dependent improvements, aligning with primate visual representations.
bioRxiv · Mar 18, 2026 · PreprintNeuroscience