AI Paper Atlas

Research map / Video / Video segmentation and tracking

JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation

Jiaming Zhang, Yutao Cui, Gangshan Wu, Limin Wang

TPAMI 2025 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 25 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
use joint modeling blocks instead of extract-then-match (ablation)JointFormer · DAVIS 2017 testJ&F: 76.2 -> 86.4Improved
make reference tokens extract features without current tokens or other refs (mode d vs a) (ablation)JointFormer · DAVIS 2017 testJ&F: 83.6 -> 86.4Improved
stop current tokens feeding references (mode d vs b) (ablation)JointFormer · DAVIS 2017 testJ&F: 83.8 -> 86.4Improved
stop references sharing with each other (mode d vs c) (ablation)JointFormer · DAVIS 2017 testJ&F: 83.9 -> 86.4Improved
make all blocks joint modeling blocks instead of first 6 (ablation)JointFormer · DAVIS 2017 valJ&F: 87.3 -> 88.1Improved
joint modeling in first 6 blocks instead of last 6 (ablation)JointFormer · DAVIS 2017 valJ&F: 87.1 -> 87.3Improved
make all blocks joint instead of evenly 2 blocks (ablation)JointFormer · DAVIS 2017 valJ&F: 86.9 -> 88.1Improved
add compressed memory updated with 2 blocks (ablation)JointFormer · DAVIS 2017 valJ&F: 88.1 -> 89.1Improved
update compressed memory with 3 blocks instead of 2 (ablation)JointFormer · DAVIS 2017 valJ&F: 89.1 -> 88.1Hurt
replace compressed memory with XMem GRU (ablation)JointFormer · DAVIS 2017 valJ&F: 88.1 -> 88.1No clear effect
add static-image pre-trainingJointFormer · DAVIS 2017 valJ&F: 89.1 -> 89.7Improved
add BL30K pre-trainingJointFormer · DAVIS 2017 valJ&F: 89.7 -> 90.1Improved

Later papers that compared with this method

1 later accepted paper reports JointFormer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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