3 papers
cs.CV2024
Text-Guided Video Masked Autoencoder
David Fan, Jue Wang, Shuai Liao +3
Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient…
cs.RO2024
UNRealNet: Learning Uncertainty-Aware Navigation Features from High-Fidelity Scans of Real Environments
Samuel Triest, David D. Fan, Sebastian Scherer +1
Traversability estimation in rugged, unstructured environments remains a challenging problem in field robotics. Often, the need for precise, accurate traversability estimation is i…
cs.CV2023
Motion-Guided Masking for Spatiotemporal Representation Learning
David Fan, Jue Wang, Shuai Liao +5
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spat…