model · first seen 6 Oct 2026
VideoMAE
Also: VideoMAEv2, video masked autoencoder
A self-supervised video transformer pretrained by reconstructing heavily masked spatiotemporal video tubes.
Mentions per week
PapersCodeDiscussion
Earliest sources
- HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic dataPapers · 6 Oct 2026 · Ricardo Pizarro, Roberto Valle, José M. Buenaposada, Luis M. Bergasa, Luis Baum…
- Video-Based Sexual Harassment Detection Using Fine-Tuned Video TransformersPapers · 11 Oct 2026 · Jubayer- Al- Mahmud, Md Shamimul Islam, Md Nur Hossain
- An Error Budget for Shuffled Multimodal Windows in the 3rd WEAR Challenge: Stacking, Count Constraints and Seam MatchingPapers · 23 Oct 2026 · Soheil Kooklan
- Detecting Temporal Concepts in Video Transformers via a No-False-Positives TestPapers · 23 Oct 2026 · Jianghuai Li, Andrew Ren, Greg Shakhnarovich
Latest sources
- Detecting Temporal Concepts in Video Transformers via a No-False-Positives TestPapers · 23 Oct 2026 · Jianghuai Li, Andrew Ren, Greg Shakhnarovich
- An Error Budget for Shuffled Multimodal Windows in the 3rd WEAR Challenge: Stacking, Count Constraints and Seam MatchingPapers · 23 Oct 2026 · Soheil Kooklan
- Video-Based Sexual Harassment Detection Using Fine-Tuned Video TransformersPapers · 11 Oct 2026 · Jubayer- Al- Mahmud, Md Shamimul Islam, Md Nur Hossain
- HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic dataPapers · 6 Oct 2026 · Ricardo Pizarro, Roberto Valle, José M. Buenaposada, Luis M. Bergasa, Luis Baum…