AI Paper Atlas

Research map / Video / Video segmentation and tracking

XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

Ho Kei Cheng, Alexander G. Schwing

ECCV 2022 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 518 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 sensory memory (ablation)XMem · Long-time Video (1x)J&F: 87.9 -> 89.8Improved
add working memory (ablation)XMem · Long-time Video (1x)J&F: 38.7 -> 89.8Improved
add long-term memory (ablation)XMem · DAVIS 2017 valFPS: 17.6 -> 22.6Improved
add long-term memory (ablation)XMem · YouTubeVOS 2018 valG: 85.9 -> 85.7No clear effect
add both shrinkage and selection terms (ablation)XMem · YouTubeVOS 2018 valG: 85.0 -> 85.7Improved
add selection term only (ablation)XMem · YouTubeVOS 2018 valG: 85.0 -> 84.8Hurt
add shrinkage term only (ablation)XMem · DAVIS 2017 valJ&F: 85.1 -> 85.6Improved
add potentiation to memory consolidation (ablation)XMem · Long-time Video (3x)J&F: 87.9 -> 90.0Improved
use usage-based instead of K-means prototype selection (P=256) (ablation)XMem · Long-time Video (3x)J&F: 74.5 -> 90.1Improved
use usage-based instead of random prototype selection (P=128) (ablation)XMem · Long-time Video (3x)J&F: 89.7 -> 90.0Improved
memory consolidation instead of eager compression (ablation)XMem · Long-time Video (3x)J&F: 87.3 -> 90.0Improved
memory consolidation instead of sparse insertion (ablation)XMem · Long-time Video (3x)J&F: 87.3 -> 90.0Improved

Later papers that compared with this method

24 later accepted papers report XMem as a baseline in their results tables; 20 of them report a better number on most of the results they share with it.

16 more not listed.

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