AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

Zezheng Wang, Zitong Yu, Chenxu Zhao, Xiangyu Zhu, Yunxiao Qin, Qiusheng Zhou, Feng Zhou, Zhen Lei

CVPR 2020 · Video › Video segmentation and tracking · approach: Deepfake video detection · 243 citations (OpenAlex)

Check 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 contrastive depth loss to the raw backbone (ablation)Face anti-spoofing depth model · OULU-NPU Protocol 3ACER (%): 6.25±3.20 -> 5.07±1.83Improved
Replace vanilla convolutions with RSGB (ablation)Model 2 · OULU-NPU Protocol 3ACER (%): 5.07±1.83 -> 3.19±0.90Improved
Add STSTB (ablation)RSGB depth model · OULU-NPU Protocol 3ACER (%): 3.19±0.90 -> 2.99±0.72Improved
Add ConvGRU (ablation)RSGB + STSTB model · OULU-NPU Protocol 3ACER (%): 2.99±0.72 -> 2.85±0.49Improved
Add binary supervision (ablation)Model 5 · OULU-NPU Protocol 3ACER (%): 2.85±0.49 -> 2.71±0.63Improved
Replace STSTB with OFF (ablation)Temporal depth model · OULU-NPU Protocol 3ACER (%): 2.71±0.63 -> 3.20±1.00Hurt
Use actual rather than generated depth supervision (ablation)Model 7 · DMADACER (%): 6.33 -> 4.55Improved
Set the temporal refinement weight α to 0.6 rather than using only spatial depth (α = 0.0) (ablation)Spatio-temporal depth refinement · OULU-NPU Protocol 3ACER (%)Improved
Vary frame sampling interval from 1 to 3 frames (ablation)Spatio-temporal architecture · OULU-NPU Protocol 3 sub-protocolACER (%): 3.347% -> 2.927%Improved
Increase frame sampling interval from 3 to 5 frames (ablation)Spatio-temporal architecture · OULU-NPU Protocol 3 sub-protocolACER (%): 2.927% -> 4.223%Hurt
Increase frame sampling interval from 3 to 7 frames (ablation)Spatio-temporal architecture · OULU-NPU Protocol 3 sub-protocolACER (%): 2.927% -> 2.934%No clear effect
Use the proposed method instead of AuxiliaryFace anti-spoofing model · SiW → OULU-NPU Protocol 3ACER (%): 13.8±5.7 -> 14.6±4.8Hurt

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