AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning to Segment Moving Objects

Pavel Tokmakov, Cordelia Schmid, Karteek Alahari

IJCV 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 126 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 appearance stream (DeepLab fc6 features) (ablation)video segmentation framework · DAVIS valmean IoU: 43.5 -> 70.1Improved
add motion stream (MP-Net) (ablation)video segmentation framework · DAVIS valmean IoU: 59.6 -> 70.1Improved
add ConvGRU memory module (ablation)video segmentation framework · DAVIS valmean IoU: 64.1 -> 70.1Improved
use ConvGRU instead of ConvRNN (ablation)memory module · DAVIS valmean IoU: 68.7 -> 70.1Improved
use ConvGRU instead of ConvLSTM (ablation)memory module · DAVIS valmean IoU: 68.9 -> 70.1No clear effect
add bidirectional processing (ablation)ConvGRU memory · DAVIS valmean IoU: 67.2 -> 70.1Improved
use PASCAL VOC pretrained DeepLab instead of ImageNet-only (ablation)appearance stream · DAVIS valmean IoU: 64.1 -> 70.1Improved
replace DeepLab-v1 VGG16 with DeepLab-v2 ResNet101 (ablation)appearance stream · DAVIS valmean IoU: 70.1 -> 72.5Improved
use conv5 instead of fc6 features (ablation)appearance stream · DAVIS valmean IoU: 70.1 -> 67.7Hurt
train memory module on DAVIS instead of synthetic FT3D (ablation)ConvGRU · DAVIS valmean IoU: 55.3 -> 70.1Improved
use FlowNet 2.0 instead of LDOF flow for MP-Net (ablation)MP-Net · DAVISmean IoU: 52.4 -> 62.6Improved
train MP-Net on FT3D + DAVIS instead of FT3D only (ablation)MP-Net · DAVIS valmean IoU: 62.6 -> 66.7Improved

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