atlas

Research map / Video / Video segmentation and tracking

Query-Memory Re-Aggregation for Weakly-supervised Video Object Segmentation

AAAI 2021 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 24 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace one-stage aggregation with two-stage re-aggregation (ablation)QMRA · DAVIS 2016Jm: 81.4 -> 84.2Helped
Align query and memory inputs consistently in the second stage (ablation)QMRA · DAVIS 2016Jm: 82.8 -> 84.2Helped
Use a shared memory encoder for query and memory features (ablation)QMRA · DAVIS 2016Jm: 82.4 -> 84.2Helped
Add Query-Memory Aggregation (ablation)QMRA · DAVIS 2016Jm: 72.2 -> 84.2Helped
Add Bidirectional Channel Aggregation (ablation)QMRA · DAVIS 2016Jm: 81.8 -> 84.2Helped
Add the Cascaded Refinement Module (ablation)QMRA · DAVIS 2016Jm: 82.2 -> 84.2Helped
Add CoordConv to CRM (ablation)QMRA · DAVIS 2016Jm: 82.8 -> 84.2Helped
Use extra memory frames (ablation)QMRA · DAVIS 2016Jm: 82.5 -> 84.2Helped
Add COCO to pre-training (ablation)QMRA · DAVIS 2016Jm: 84.2 -> 84.7Helped

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