AI Paper Atlas

Research map / Video / Video segmentation and tracking

Robust Promptable Video Object Segmentation

Sohyun Lee, Yeho Gwon, Lukas Hoyer, Konrad Schindler, Christos Sakaridis, Suha Kwak

CVPR 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 0 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 memory conditioning of the gate (ablation)MoGA · MVSeg-advJ&F: 69.6 -> 70.9Improved
add per-object conditioning on top of memory conditioning (ablation)MoGA · MVSeg-advJ&F: 70.9 -> 71.8Improved
use MoGA instead of LoRASAM2 · MVSeg-advJ&F: 70.9 -> 71.8Improved
use MoGA with 1.1M params instead of full fine-tuning of 80.9M paramsSAM2 · MVSeg-advJ&F: 71.5 -> 71.8Improved
add MoGA to SAM2SAM2 · ACDC-VideoJ&F: 63.5 -> 64.5Improved
add MoGA to SAM2SAM2 · YouTube-VOS-CJ&F: 78.7 -> 79.9Improved
add MoGA to SAM2SAM2 · YouTube-VOS (clean)J&F: 82.2 -> 82.6No clear effect
add MoGA to SAM2 on long videosSAM2 · MVSeg-adv long videos (~42s)J&F: 52.3 -> 56.2Improved
apply GaRA frame-wise before SAM2SAM2 · YouTube-VOS-CJ&F: 78.7 -> 78.1Hurt
apply restoration (AirNet) before SAM2SAM2 · ACDC-VideoJ&F: 63.5 -> 59.8Hurt
increase adapter rank from 128 to 256 or 512 (ablation)MoGA · YouTube-VOS-CJ&F: 79.9 -> 79.8, 79.7Hurt
reduce adapter rank from 128 to 32 (ablation)MoGA · YouTube-VOS-CJ&F: 79.9 -> 79.3Hurt

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