AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Object Segmentation by Learning Location-Sensitive Embeddings

Hai Ci, Chunyu Wang, Yizhou Wang

ECCV 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 62 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 zooming-in on estimated object box (ablation)FP · DAVIS val (first-frame box)J mean: 70.5 -> 76.2Improved
jointly train location-sensitive embedding branch with foreground branch (ablation)FP · DAVIS val (first-frame box)J mean: 76.2 -> 80.0Improved
jointly train location-sensitive embedding branch (ablation)FP · DAVIS val (first-frame box)F mean: 75.0 -> 79.1Improved
fuse embedding-based foreground map with foreground prediction (ablation)FPLSE · DAVIS val (first-frame box)J mean: 80.0 -> 81.0Improved
add per-video model adaptation with pseudo-labels (ablation)Ours (static) · DAVIS val (first-frame box)J mean: 80.0 -> 81.0Improved
add per-video model adaptation with pseudo-labels (ablation)Ours (static) · DAVIS val (first-frame box)F recall: 87.0 -> 89.1Improved
add CRF post-processingOurs · DAVIS val (first-frame box)J mean: 81.0 -> 82.9Improved
add CRF post-processingOurs · DAVIS val (first-frame box)F mean: 80.3 -> 80.1No clear effect
add location-sensitive embeddings to foreground prediction (GT boxes) (ablation)FP · DAVIS val (GT boxes all frames)J mean: 80.4 -> 80.9Improved
replace GrabCut with learned foreground prediction networkGrabCut · DAVIS val (GT boxes all frames)J mean: 61.5 -> 80.4Improved
add location-sensitive embeddings to foreground prediction (GT boxes) (ablation)FP · DAVIS val (GT boxes all frames)F mean: 80.2 -> 80.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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