1. Detection of Digital Face Manipulation Source Code

    The prevalence of facial recognition, biometric unlock, and social media presents a significant opportunity for bad actors to introduce forged or manipulated images to spread false information or damage reputations. This is aided by the continuing improvement in realistic image synthesis and manipulation by generative adversarial network, GAN, based methods ...

    Continue reading

    Keywords: Fake Faces, Attention Mechanism

  2. DFFD: Diverse Fake Face Dataset

    The prevalence of facial recognition, biometric unlock, and social media presents a significant opportunity for bad actors to introduce forged or manipulated images to spread false information or damage reputations. This is aided by the continuing improvement in realistic image synthesis and manipulation by generative adversarial network, GAN, based methods ...

    Continue reading

    Keywords: Fake Faces, Attention Mechanism

  3. Generic Object Anti-Spoofing Source Code

    Biometric recognition is increasingly used in society for commercial applications and high-level security. However, recent works are not generalizable between the biometric modalities. We use live and spoof videos of generic objects to model the noise patterns for camera sensors and spoof mediums, and synthesize seen and unseen combinations of ...

    Continue reading

    Keywords: Anti-Spoofing, Noise Synthesis

  4. Frontal View Gait(FVG) Database

    Compare to other view angles in gait recognition, frontal-view walking is a more challenging problem since it contains minimal gait cues. To facilitate this research, we collect the Front-View Gait (FVG) database in the course of two years, 2017 and 2018. FVG includes significant variations, e.g., walking speed, carrying ...

    Continue reading

    Keywords: Gait Recognition

  5. SiW: Spoof in the Wild Database

    To benchmark face anti-spoofing methods specifically for unknown attacks, we collect the Spoof in the Wild database with Multiple Attack Types (SiW-M). SiW-M shows a great diversity in spoof attacks, subject identities, environments and other factors.

    Continue reading

    Keywords: Face antispoofing

  6. PIFA Source Code

    Dense Face Alignment implementation may be downloaded from here.

    Pose-Invariant Face Alignment with a Single CNN implementation may be downloaded from here.

    PIFA implementation may be downloaded from here.

    The part of AFLW database used for training and testing can be found from here.

    If you use PIFA code, please ...

    Continue reading

    Keywords: Face alignment

  7. Typing Behavior Dataset

    This dataset is released in two different forms. Acoustics: 45 subjects from phase 1. Visual: Full dataset. Typing Behavior Dataset may be downloaded from here.

    We collect a first-of-its kind keystroke database in two phases. Phase 1 includes 56 subjects typing multiple same day, fixed and free text, sessions. It ...

    Continue reading

    Keywords: Typing behavior