AI Paper Atlas

Research map / Video / Video segmentation and tracking

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Shuangrui Ding, Rui Qian, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Yuwei Guo, Dahua Lin, Jiaqi Wang

ICCV 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 73 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 constrained memory tree search with P=3 pathways (ablation)SAM2-L · SA-V valJ&F: 76.3 -> 80.8Improved
add constrained memory tree search with P=3 pathways (ablation)SAM2-L · LVOS v2 valJ&F: 83.0 -> 85.4Improved
increase pathways from 3 to 4 (ablation)SAM2Long · SA-V valJ&F: 80.8 -> 80.7No clear effect
use 2 pathways instead of 1 (ablation)SAM2-L · SA-V valJ&F: 76.3 -> 80.1Improved
use 3 pathways instead of 1 (cost) (ablation)SAM2-L · SA-V valFPS: 22 -> 19Hurt
add temporal decay to IoU-based memory frame selection (ablation)SAM2Long · SA-V valJ&F: 80.8 -> 80.4Hurt
add spatial similarity to IoU-based memory frame selection (ablation)SAM2Long · LVOS v2 valJ&F: 85.4 -> 84.8Hurt
round predicted IoU to select diverse masks (ablation)SAM2Long · LVOS v2 valJ&F: 84.4 -> 85.4Improved
round predicted IoU to select diverse masks (ablation)SAM2Long · SA-V valactual pairwise IoU: 84.5 -> 51.4Improved
add IoU threshold of 0.3 for memory frames (vs none) (ablation)SAM2Long · SA-V valJ&F: 80.0 -> 80.8Improved
set uncertainty threshold to 2 instead of 0 (ablation)SAM2Long · LVOS v2 valJ&F: 84.4 -> 85.4Improved
use modulation weights [0.95,1.05] instead of none [1,1] (ablation)SAM2Long · LVOS v2 valJ&F: 84.9 -> 85.4Improved

Later papers that compared with this method

2 later accepted papers report SAM2Long as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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