Motion-Guided Masking for Spatiotemporal Representation Learning

The authors used several video benchmarks, including Kinetics-400 and Something-Something V2, to evaluate their proposed motion-guided masking algorithm.

Data and Resources

Cite this as

David Fan, Jue Wang, Hector Santos-Villalobos, Shuai Liao, Yi Zhu, Vimal Bhat, Rohith MV, Xinyu Li (2024). Dataset: Motion-Guided Masking for Spatiotemporal Representation Learning. https://doi.org/10.57702/gda8x1nb

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author David Fan
More Authors
Jue Wang
Hector Santos-Villalobos
Shuai Liao
Yi Zhu
Vimal Bhat
Rohith MV
Xinyu Li
Homepage https://arxiv.org/abs/2203.12602