Efficient Video Understanding

Z Wu, YG Jiang - Deep Learning for Video Understanding, 2024‏ - Springer
Video understanding requires substantially more computing resources compared to their
image counterparts due to the additional temporal dimension. As a result, the development …

[كتاب][B] Deep Learning for Video Understanding

Z Wu, YG Jiang - 2024‏ - Springer
Video understanding is a critical technique which aims to recognize the objects and
activities in videos and further analyze their evolution over time. In an era dominated by …

Efficient VideoMAE via Temporal Progressive Training

X Li, P Wang, X Li, H Wang, C **e‏ - openreview.net
Masked autoencoders (MAE) have recently been adapted for video recognition, setting new
performance benchmarks. Nonetheless, the computational overhead of training VideoMAE …