AI Paper Atlas

Research map / Video / Video segmentation and tracking

Face Mask Extraction in Video Sequence

Yujiang Wang, Bingnan Luo, Jie Shen, Maja Pantić

IJCV 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 26 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 5-frame Gaussian temporal smoothing to the predictions (ablation)FCN-ResNet50 · 300VW-Mask testmean IoU (%): 54.50 -> 54.21No clear effect
Add a ConvLSTM layer (other layers frozen, Adam) (ablation)FCN-ResNet50 · 300VW-Mask testmean IoU (%): 54.50 -> 55.53Improved
Use Adam instead of RMSprop for the ConvLSTM layer (ablation)ConvLSTM-FCN · 300VW-Mask testmean IoU (%): 54.93 -> 55.53Improved
Replace cross-entropy with IoU loss (ablation)ConvLSTM-FCN (frozen) · 300VW-Mask testmean IoU (%): 55.53 -> 57.22Improved
Replace cross-entropy with Segmentation Loss (g=0) (ablation)ConvLSTM-FCN (frozen) · 300VW-Mask testmean IoU (%): 55.53 -> 59.04Improved
Use Segmentation Loss (g=0) instead of IoU loss (ablation)ConvLSTM-FCN (frozen) · 300VW-Mask testmean IoU (%): 57.22 -> 59.04Improved
Unfreeze other layers with reduced learning rate (gamma=0.05) (ablation)ConvLSTM-FCN with SegLoss · 300VW-Mask testmean IoU (%): 59.04 -> 60.04Improved
Vary gamma from 0.01 to 0.1 for the primary model (ablation)Primary ConvLSTM-FCN · 300VW-Mask testmean IoU (%): 60.35, 60.96, 60.04, 60.07No clear effect
Add ConvLSTM with gamma=0.1 to the eye model (ablation)Eye baseline-FCN · Eye sub-datasetEyes IoU (%): 54.29 -> 51.82Hurt
Add ConvLSTM with gamma=0.02 to the eye model (ablation)Eye baseline-FCN · Eye sub-datasetEyes IoU (%): 54.29 -> 59.01Improved
Add ConvLSTM to the mouth model (gamma=0.02) (ablation)Mouth baseline-FCN · Mouth sub-datasetmean IoU (%): 49.77 -> 52.17Improved
Add the two additional eye and mouth models to the primary model (ablation)Primary model · 300VW-Mask testmean IoU (%): 60.04 -> 63.76Improved

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