AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatial-Temporal Multi-level Association for Video Object Segmentation

Deshui Miao, Xin Li, Zhenyu He, Huchuan Lu, Ming-Hsuan Yang

ECCV 2024 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 6 citations (OpenAlex)

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 object features to the STML module (ablation)STMA · DAVIS 2017 testJ&F: 83.8 -> 85.6Improved
add reference frames from spatial memory to STML input (ablation)STMA · DAVIS 2017 valJ&F: 87.8 -> 88.9Improved
add temporal memory with ID association (ablation)STMA · DAVIS 2017 testJ&F: 81.0 -> 85.6Improved
add temporal memory with ID association (ablation)STMA · DAVIS 2017 valFPS: 3.5 -> 10.7Improved
use decoupled three-stream STML attention instead of joint self-attention (ablation)STMA · DAVIS 2017 testJ&F: 82.7 -> 85.6Improved
use MAE pre-trained weights instead of training from scratch (ablation)STMA ConvViTb · DAVIS 2017 valJ&F: 83.6 -> 88.9Improved
use MAE instead of MoCoV3 pre-trained weights (ablation)STMA ViTb · DAVIS 2017 valJ&F: 84.1 -> 88.2Improved
add static-image pre-trainingSTMA · DAVIS 2017 valJ&F: 88.9 -> 90.4Improved
add BL30K pre-trainingSTMA · DAVIS 2017 test-devJ&F: 87.1 -> 87.7Improved
evaluate on DAVIS 2016 against SimVOS-BSTMA · DAVIS 2016 valJ&F: 92.9 -> 91.6Hurt

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