# Face Mask Extraction in Video Sequence

arXiv: https://arxiv.org/abs/1807.09207 · HTML: https://mlsanity.com/paper/1807.09207/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 6 of 6)

- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Sequential vessel segmentation via deep channel attention network](https://mlsanity.com/paper/2102.05229/) (2021)
- [DAViD: Data-efficient and Accurate Vision Models from Synthetic Data](https://mlsanity.com/paper/2507.15365/) (2025)
- [A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline](https://mlsanity.com/paper/2104.04443/) (2021)
- [Efficient Video Segmentation Models with Per-frame Inference](https://mlsanity.com/paper/2202.12427/) (2022)

## Abstract (arXiv)

Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence. Comparing to landmark-based sparse face shape representation, our method can produce the segmentation masks of individual facial components, which can better reflect their detailed shape variations. By integrating Convolutional LSTM (ConvLSTM) algorithm with Fully Convolutional Networks (FCN), our new ConvLSTM-FCN model works on a per-sequence basis and takes advantage of the temporal correlation in video clips. In addition, we also propose a novel loss function, called Segmentation Loss, to directly optimise the Intersection over Union (IoU) performances. In practice, to further increase segmentation accuracy, one primary model and two additional models were trained to focus on the face, eyes, and mouth regions, respectively. Our experiment shows the proposed method has achieved a 16.99% relative improvement (from 54.50% to 63.76% mean IoU) over the baseline FCN model on the 300 Videos in the Wild (300VW) dataset.