AI Paper Atlas

Research map / Video / Video segmentation and tracking

Test-Time Training on Video Streams

Renhao Wang, Yu Sun, Arnuv Tandon, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang

JMLR 2025 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 21 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 implicit memory (init from previous model) to TTT-MAE (ablation)TTT-MAE · COCO Videos instance segmentationAP: 17.2 -> 18.3Improved
add explicit memory (sliding window) to TTT-MAE (ablation)TTT-MAE · COCO Videos instance segmentationAP: 17.2 -> 17.7Improved
add explicit memory on top of implicit memory (ablation)Online TTT-MAE · COCO Videos panoptic segmentationPQ: 22.7 -> 24.3Improved
add implicit memory on top of explicit memory (ablation)Online TTT-MAE · KITTI-STEP testmean IoU (%): 52.5 -> 54.5Improved
add explicit memory to implicit-only TTT (ablation)Online TTT-MAE · KITTI-STEP valmean IoU (%): 54.3 -> 55.6Improved
online TTT-MAE instead of Main Task OnlyMask2Former · COCO Videos instance segmentationAP: 13.4 -> 19.4Improved
online TTT-MAE instead of Main Task OnlyMask2Former · COCO Videos panoptic segmentationPQ: 14.6 -> 24.3Improved
online TTT-MAE instead of Main Task OnlyMask2Former · KITTI-STEP valmean IoU (%): 53.8 -> 55.6Improved
online streaming TTT-MAE vs offline MAE on all framesTTT-MAE · COCO Videos panoptic segmentationPQ: 20.3 -> 24.3Improved
adapt normalization layers (LN Adapt, Tent)Main Task Only · KITTI-STEP testmean IoU (%): 52.5 -> 52.2No clear effect
joint training with MAE taskMain Task Only · COCO Videos instance segmentationAP: 13.4 -> 13.0No clear effect
add temporal smoothing (ablation)Main Task Only · KITTI-STEP valmean IoU (%): +0.4% mean IoUNo clear effect

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