AI Paper Atlas

Research map / Video / Video segmentation and tracking

BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation

Ye Yu, Jialin Yuan, Gaurav Mittal, Li Fuxin, Mei Chen

ECCV 2022 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 38 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
use bilateral attention instead of spatial local attention (ablation)BATMAN · DAVIS 2017 valJ&F: 84.9 -> 86.2Improved
use bilateral attention instead of spatial local attention (ablation)BATMAN · DAVIS 2017 test-devJ&F: 77.5 -> 82.2Improved
use bilateral attention instead of spatial local attention (ablation)BATMAN · DAVIS 2016 valJ&F: 91.6 -> 92.5Improved
use bilateral attention instead of spatial local attention (ablation)BATMAN · YouTube-VOS 2019 valJ&F: 84.1 -> 85.0Improved
use bilateral attention instead of spatial local attention (ablation)BATMAN · YouTube-VOS 2018 valJ&F: 83.8 -> 85.3Improved
add optical flow calibration to bilateral attention (ablation)BATMAN · DAVIS 2017 valJ&F: 86.0 -> 86.2Improved
add optical flow calibration to bilateral attention (ablation)BATMAN · DAVIS 2017 test-devJ&F: 81.7 -> 82.2Improved
add optical flow calibration to bilateral attention (ablation)BATMAN · DAVIS 2016 valJ&F: 92.4 -> 92.5Improved
add optical flow calibration to bilateral attention (ablation)BATMAN · YouTube-VOS 2019 valJ&F: 84.6 -> 85.0Improved
add optical flow calibration to bilateral attention (ablation)BATMAN · YouTube-VOS 2018 valJ&F: 84.8 -> 85.3Improved

Later papers that compared with this method

1 later accepted paper reports BATMAN as a baseline in their results tables; 0 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