AI Paper Atlas

Research map / Video / Video segmentation and tracking

MaskViT: Masked Visual Pre-Training for Video Prediction

Agrim Gupta, Stephen Tian, Yunzhi Zhang, Jiajun Wu, Roberto Martín-Martín, Li Fei-Fei

ICLR 2023 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 44 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Condition predictions on the goal frameMaskViT · BAIRFVD: 93.7 -> 76.9Improved
Condition predictions on actionsMaskViT · BAIRFVD: 93.7 -> 70.5Improved
Use variable training mask ratios rather than fixed ratios (ablation)MaskViT · BAIRFVD: 96.6 vs. 110.9Improved
Increase embedding dimension from 768 to 1024 (ablation)MaskViT · BAIRFVD: 96.6 -> 94.2Improved
Increase transformer blocks from 6 to 8 (ablation)MaskViT · BAIRFVD: 96.6 -> 99.3Hurt
Use the 16×4×4 spatiotemporal window instead of full self-attention (ablation)MaskViT · BAIRFVD: 98.2 -> 96.6Improved
Use fixed mask ratio 0.98 (ablation)MaskViT · BAIRFVD: 96.6 -> 214.4Hurt
Use concave rather than linear or convex mask scheduling (ablation)MaskViT iterative decoding · Video prediction datasetsFVDImproved
Add temperature-annealed Gumbel noise to token confidence (ablation)MaskViT iterative decoding · Video prediction datasetsmotion diversityImproved
Increase decoding iterations beyond the point where FVD stops improving (ablation)MaskViT iterative decoding · Video prediction datasetsFVDNo clear effect
Add domain-specific finetuning dataMaskViT robot planner · Real robot table setting and sweepingsuccesses: 1/30 -> 16/30Improved
Combine domain-specific data during training versus post-finetuning (ablation)MaskViT robot planner · Real robot table setting and sweepingsuccesses: 18/30 vs. 16/30No clear effect

Later papers that compared with this method

4 later accepted papers report MaskViT as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy