AI Paper Atlas

Research map / Video / Video segmentation and tracking

STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond

Zheng Chang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao

TPAMI 2025 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 5 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
add temporal attention module (T_AMI) (ablation)STAU · Moving MNISTMSE: 29.9 -> 27.1Improved
add temporal attention module (T_AMI) (ablation)STAU · Moving MNISTSSIM: 0.933 -> 0.939Improved
add temporal-from-spatial attention (S->T) (ablation)STAU · Moving MNISTMSE: 31.2 -> 29.6Improved
add spatial-from-temporal attention (T->S) (ablation)STAU · Moving MNISTMSE: 31.2 -> 29.5Improved
use both S->T and T->S correlations (ablation)STAU · Moving MNISTMSE: 29.5 -> 27.1Improved
increase temporal and spatial receptive field to tau=5, theta=5 (ablation)STAU · Moving MNISTMSE: 33.4 -> 27.1Improved
increase temporal receptive field tau from 1 to 5 at theta=1 (ablation)STAU · Moving MNISTMSE: 33.4 -> 29.5Improved
increase spatial receptive field theta from 1 to 5 at tau=1 (ablation)STAU · Moving MNISTMSE: 33.4 -> 29.9Improved
replace MAU unit with STAU unit (ablation)video prediction model · Moving MNISTMSE: 29.5 -> 27.1Improved
add STAU predictive unit as video predictor before classification (ablation)classifier · Something-SomethingV2 front 25%top-1: 2.10 -> 7.50Improved
use STAU instead of MAU (ablation)early action recognition · Something-SomethingV2 front 50%top-1: 10.60 -> 12.90Improved
use STAU instead of MAU (ablation)parameters and inference time · Moving MNISTinference time (s/800 samples): 17.34 -> 19.58Hurt

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