AI Paper Atlas

Research map / Video / Video segmentation and tracking

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation

Fu Rong, Meng Lan, Qian Zhang, Lefei Zhang

ICCV 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 13 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 mask-text similarity loss (ablation)baseline SAM 2 + multimodal encoder · Ref-YouTube-VOS valJ&F: 69.4 -> 70.3Improved
Add mask prior generator (ablation)baseline + L_sim · Ref-YouTube-VOS valJ&F: 70.3 -> 71.9Improved
Add hierarchical global-historical aggregator (ablation)baseline + L_sim · Ref-YouTube-VOS valJ&F: 70.3 -> 72.3Improved
Add both MPG and HGA (ablation)baseline + L_sim · Ref-YouTube-VOS valJ&F: 70.3 -> 73.9Improved
Use per-frame prompts instead of first-frame only (ablation)baseline · Ref-YouTube-VOS valJ&F: 59.0 -> 69.4Improved
Add SAM 2 memory mechanism (ablation)baseline · Ref-YouTube-VOS valJ&F: 66.2 -> 69.4Improved
Add spatiotemporal self-interaction in MPG (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.3 -> 73.9Improved
Add spatiotemporal cross-modal interaction in MPG (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.5 -> 73.9Improved
Use patch size 2 instead of 1 or 4 in HGA (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.2 -> 73.9Improved
Use masked global video feature instead of vanilla (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.1 -> 73.9Improved
Increase pixel-level fusion layers from 1 to 3 (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.9 -> 73.0Hurt
Increase object-level fusion layers from 1 to 3 (ablation)MPG-SAM 2 · Ref-YouTube-VOS valJ&F: 73.9 -> 72.9Hurt

Later papers that compared with this method

2 later accepted papers report MPG-SAM 2 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 1 of 1 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