Extending Video Masked Autoencoders to 128 frames
–Neural Information Processing Systems
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.
Neural Information Processing Systems
Feb-18-2026, 09:07:39 GMT
- Country:
- North America > Canada > British Columbia (0.04)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Media (0.46)
- Technology: