AI Paper Atlas

Research map / Video / Video segmentation and tracking

Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration

Zongxin Yang, Yunchao Wei, Yi Yang

TPAMI 2021 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 161 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 background embedding (foreground and background) to matching and attention (ablation)CFBI · DAVIS-2017 valAvg J&F: 70.9 -> 74.9Improved
add background embedding to pixel-level matching (ablation)CFBI · DAVIS-2017 valAvg J&F: 73.0 -> 74.9Improved
add background embedding to instance-level attention (ablation)CFBI · DAVIS-2017 valAvg J&F: 72.3 -> 74.9Improved
add foreground and background bias b_F, b_B to distance metric (ablation)CFBI · DAVIS-2017 valAvg J&F: 72.8 -> 74.9Improved
use multi-local windows instead of one local window (ablation)CFBI · DAVIS-2017 valAvg J&F: 73.8 -> 74.9Improved
add sequential training with predicted previous masks (ablation)CFBI · DAVIS-2017 valAvg J&F: 73.3 -> 74.9Improved
use collaborative ensembler instead of 4 separable conv layers (ablation)CFBI · DAVIS-2017 valAvg J&F: 73.3 -> 74.9Improved
add balanced random-crop (ablation)CFBI · DAVIS-2017 valAvg J&F: 72.8 -> 74.9Improved
add instance-level attention guidance to the ensembler (ablation)CFBI · DAVIS-2017 valAvg J&F: 72.7 -> 74.9Improved
atrous factor 2 in global matching (ablation)CFBI · YouTube-VOS 2018 valAvg J&F: 81.4 -> 81.3No clear effect
increase atrous factor from 1 to 4 in multi-local matching (ablation)CFBI · YouTube-VOS 2018 valAvg J&F: 81.4 -> 79.5Hurt
do matching at stride 4 instead of stride 16 (ablation)CFBI · YouTube-VOS 2018 valAvg J&F: 78.3 -> 81.6Improved

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