AI Paper Atlas

Research map / Video / Video segmentation and tracking

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

Ali Athar, Sabarinath Mahadevan, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe

ECCV 2020 · Video › Video segmentation and tracking · approach: Matching-based video object 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 spatial coordinate offset to the embedding mixing function (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 57.3 -> 61.6Improved
add a temporal coordinate offset dimension (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 61.6 -> 62.6Improved
use a free embedding dimension instead of a temporal dimension (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 62.6 -> 62.8Improved
use E=4 with two free dimensions instead of temporal+free (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 64.2 -> 64.4Improved
add a fifth embedding dimension (E=5) (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 64.4 -> 62.4Hurt
increase clip length from T=4 to T=8 (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 62.2 -> 64.4Improved
increase clip length from T=8 to T=16 (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 64.4 -> 64.7Improved
increase clip length from T=16 to T=24 (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 64.7 -> 63.1Hurt
add video data to image-only training (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 57.1 -> 64.4Improved
add image-augmented data to video-only training (ablation)STEm-Seg · DAVIS 2019 unsupervised valJ&F: 60.7 -> 64.4Improved
use oracle category labels instead of predicted ones (ablation)STEm-Seg · YouTube-VIS custom val splitAP: 24.7 -> 33.0Improved
use ResNet-101 instead of ResNet-50 backboneSTEm-Seg · YouTube-VIS valAP: 30.6 -> 34.6Improved

Later papers that compared with this method

11 later accepted papers report STEm-Seg as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.

3 more not listed.

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