# On Improving Temporal Consistency for Online Face Liveness Detection

arXiv: https://arxiv.org/abs/2006.06756 · HTML: https://mlsanity.com/paper/2006.06756/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [Consistency Regularization for Deep Face Anti-Spoofing](https://mlsanity.com/paper/2111.12320/) (2021)
- [Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2503.22984/) (2025)
- [Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution](https://mlsanity.com/paper/2211.13964/) (2022)
- [Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results](https://mlsanity.com/paper/2304.05753/) (2023)
- [Principles of Designing Robust Remote Face Anti-Spoofing Systems](https://mlsanity.com/paper/2406.03684/) (2024)
- [Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems](https://mlsanity.com/paper/2407.08514/) (2024)
- [Online Adaptive Personalization for Face Anti-spoofing](https://mlsanity.com/paper/2207.12272/) (2022)
- [Face Presentation Attack Detection](https://mlsanity.com/paper/2212.03680/) (2022)
- [Time-Aware Face Anti-Spoofing with Rotation Invariant Local Binary Patterns and Deep Learning](https://mlsanity.com/paper/2408.14829/) (2024)

## Abstract (arXiv)

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency across time. To address the issue, a simple yet effective solution based on temporal consistency is proposed. Specifically, in the training stage, to integrate the temporal consistency constraint, a temporal self-supervision loss and a class consistency loss are proposed in addition to the softmax cross-entropy loss. In the deployment stage, a training-free non-parametric uncertainty estimation module is developed to smooth the predictions adaptively. Beyond the common evaluation approach, a video segment-based evaluation is proposed to accommodate more practical scenarios. Extensive experiments demonstrated that our solution is more robust against several presentation attacks in various scenarios, and significantly outperformed the state-of-the-art on multiple public datasets by at least 40% in terms of ACER. Besides, with much less computational complexity (33% fewer FLOPs), it provides great potential for low-latency online applications.