AI Paper Atlas

Research map / Video / Video segmentation and tracking

DVIS++: Improved Decoupled Framework for Universal Video Segmentation

Tao Zhang, Xingye Tian, Yikang Zhou, Shunping Ji, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Yu Wu

TPAMI 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 55 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

add contrastive loss to segmenter · OVIS val (ResNet-50) · AP: 25.0 -> 25.8 No clear effect

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 contrastive loss to segmenter (ablation)MinVIS baseline · OVIS val (ResNet-50)AP: 25.0 -> 25.8No clear effect
add referring tracker (ablation)DVIS++ · OVIS val (ResNet-50)AP: 25.8 -> 32.8Improved
add denoising training strategy (ablation)DVIS++ · OVIS val (ResNet-50)AP: 32.8 -> 36.5Improved
add contrastive loss to referring tracker (ablation)DVIS++ · OVIS val (ResNet-50)AP: 36.5 -> 37.2Improved
add temporal refiner (ablation)DVIS++ · OVIS val (ResNet-50)AP: 37.2 -> 41.2Improved
add contrastive loss to temporal refiner (ablation)DVIS++ · OVIS val (ResNet-50)AP: 41.2 -> 40.6Hurt
use referring cross-attention instead of standard (ablation)referring tracker · OVIS val (ResNet-50)AP: 28.3 -> 32.8Improved
match Q_Seg with Hungarian before using as initial value (ablation)referring tracker · OVIS val (ResNet-50)AP: 31.9 -> 32.8Improved
use learnable embedding instead of matched Q_Seg as initial value (ablation)referring tracker · OVIS val (ResNet-50)AP: 32.8 -> 33.1No clear effect
add long-term attention to temporal refiner (ablation)temporal refiner · OVIS val (ResNet-50)AP: 37.0 -> 40.2Improved
add self-attention to temporal refiner (ablation)temporal refiner · OVIS val (ResNet-50)AP: 38.5 -> 40.2Improved
add cross-attention to temporal refiner (ablation)temporal refiner · OVIS val (ResNet-50)AP: 39.4 -> 40.2Improved

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