AI Paper Atlas

Research map / Video / Video segmentation and tracking

Recurrent Graph Neural Networks for Video Instance Segmentation

Emil Brissman, Joakim Johnander, Martin Danelljan, Michael Felsberg

IJCV 2022 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 19 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
use full graph neural network information flow over all tracks and detections (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 28.6 -> 35.3Improved
predict association with the GNN instead of a hand-made rule (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 29.2 -> 35.3Improved
add appearance model (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 34.5 -> 35.3Improved
learn appearance variance instead of constant (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 33.0 -> 35.3Improved
Gaussian appearance with learnable update instead of LSTM update (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 34.0 -> 35.3Improved
treat appearance separately instead of baking into embedding (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 34.4 -> 35.3Improved
score tracks from track embeddings instead of averaging detection confidence (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 31.5 -> 35.3Improved
score tracks from embeddings instead of averaging YOLACT scores (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 30.7 -> 35.3Improved
add LSTM-like gating to the recurrent connection (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: Diverges -> 35.3Improved
use full LSTM-like gating instead of a single gate with tanh (ablation)track model · YouTubeVIS val (ablation, ResNet50)mAP: 31.5 -> 35.3Improved
replace ResNet50 with ResNet101 backbonetrack model · YouTubeVIS val (ablation, ResNet50)mAP: 35.3 -> 37.7Improved
use sigmoid-gated node updates instead of 2-layer MLP (ablation)GNN · YouTubeVIS val (ablation, ResNet50)mAP: 34.1 -> 35.3Improved

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