AI Paper Atlas

Research map / Video / Video segmentation and tracking

USTEP: Spatio-Temporal Predictive Learning Under a Unified View

Cheng Tan, Jue Wang, Zhangyang Gao, Siyuan Li, Stan Ziqing Li

TPAMI 2025 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling

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 cross-segment mechanism (ablation)USTEP w/TAU · Moving MNIST (10->10)MSE: 24.01 -> 21.84Improved
use stride dt=5 instead of dt=1 (ablation)USTEP w/TAU · Moving MNIST (10->10)MSE: 31.94 -> 21.84Improved
use stride dt=5 instead of dt=10 (ablation)USTEP w/TAU · Moving MNIST (10->10)MSE: 25.13 -> 21.84Improved
use stride dt=5 instead of dt=2 (ablation)USTEP w/TAU · Moving MNIST (10->10)MSE: 24.62 -> 21.84Improved
use stride dt=5 instead of dt=1 (ablation)USTEP w/TAU · Moving MNIST (10->10)training time (s/epoch): 600 -> 93Hurt
wrap TAU in USTEPTAU · Moving MNIST (10->10)MSE: 24.60 -> 21.84Improved
wrap Uniformer in USTEPUniformer · Moving MNIST (10->10)MSE: 30.38 -> 28.51Improved
wrap SimVP in USTEPSimVP · Moving MNIST (10->10)MSE: 32.15 -> 30.04Improved
wrap TAU in USTEPTAU · Moving MNIST (10->10)Params (M): 44.7 -> 18.9Improved
wrap TAU in USTEPTAU · KTH (10->40)FVD: 1500.63 -> 849.16Improved
wrap TAU in USTEPTAU · KTH (10->20)FLOPs (G): 73.8 -> 107.0Hurt
wrap TAU in USTEPTAU · SEVIR (13->12)CSI: 0.3941 -> 0.4366Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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