AI Paper Atlas

Research map / Video / Video segmentation and tracking

Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory

Zhengtong Zhu, Jiaqing Fan, Zhixuan Liu, Fanzhang Li

AAAI 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 2 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
replace first-frame sampling with global sampling (ablation)SDAM · Ref-DAVIS17 valJ&F: 69.2 -> 73.4Improved
add Motion Driven Sampler over global sampling (ablation)SDAM · Ref-DAVIS17 valJ&F: 73.4 -> 76.0Improved
add Motion Driven Sampler over global sampling (ablation)SDAM · MeViS valJ&F: 54.4 -> 55.8Improved
raise MLLM confidence weight a from 0.4 to 0.75 (ablation)SDAM · Ref-DAVIS17 valJ&F: 73.9 -> 76.0Improved
raise MLLM confidence weight a from 0.4 to 0.6, then 0.75 (ablation)SDAM · ReasonVOSJ&F: 54.1 -> 55.1 (a=0.6) -> 54.7 (a=0.75)Mixed
use top-n keyframes (n=2,3) instead of a single keyframe (ablation)SDAM · Ref-DAVIS17 val (global sampling)J&F: 73.4 -> 70.7 (n=2), 68.6 (n=3)Hurt
training-free SDAM versus trained DMVS/SSASDAM · MeViS valJ&F: 48.6 vs 48.6No clear effect
training-free SDAM versus best prior methodSDAM · Ref-DAVIS17 valJ&F: 70.4 -> 76.0Improved
training-free SDAM versus GLUSSDAM · ReasonVOSJ&F: 49.9 -> 55.1Improved
training-free SDAM versus GLUSSDAM · ReVOS val (Overall)J&F: 54.9 -> 58.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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