Disentanglement Translation Network for multimodal sentiment analysis

Y Zeng, W Yan, S Mai, H Hu - Information Fusion, 2024 - Elsevier
Obtaining an effective joint representation has always been the goal for multimodal tasks.
However, distributional gap inevitably exists due to the heterogeneous nature of different …

Face spoofing detection based on multi-scale color inversion dual-stream convolutional neural network

X Shu, X Li, X Zuo, D Xu, J Shi - Expert Systems with Applications, 2023 - Elsevier
Currently, face recognition technology (FRT) has been applied ubiquitously. However, due
to the abuse of personal face photos on social media, FRT has encountered unprecedented …

S-adapter: Generalizing vision transformer for face anti-spoofing with statistical tokens

R Cai, Z Yu, C Kong, H Li, C Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition
system by presenting spoofed faces. State-of-the-art FAS techniques predominantly rely on …

Unmasking Deception: A Comprehensive Survey on the Evolution of Face Anti-spoofing Methods

A Antil, C Dhiman - Neurocomputing, 2024 - Elsevier
With the growing popularity of facial recognition (FR) in access control systems, there has
been a corresponding increase in presentation attacks (PAs) to gain unauthorized access …

Semantic disentanglement adversarial hashing for cross-modal retrieval

M Meng, J Sun, J Liu, J Yu, J Wu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Cross-modal hashing has gained considerable attention in cross-modal retrieval due to its
low storage cost and prominent computational efficiency. However, preserving more …

HRInversion: High-resolution GAN inversion for cross-domain image synthesis

P Zhou, L Xie, B Ni, L Liu, Q Tian - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
We investigate GAN inversion problems of using pre-trained GANs to reconstruct real
images. Recent methods for such problems typically employ a VGG perceptual loss to …

Instance paradigm contrastive learning for domain generalization

Z Chen, W Wang, Z Zhao, F Su, A Men… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Domain Generalization (DG) aims to develop models that can learn from data in source
domains and generalize to unseen target domains. Recently, some domain generalization …

Dynamic residual distillation network for face anti-spoofing with feature attention learning

Y He, F Peng, M Long - IEEE Transactions on Biometrics …, 2023 - ieeexplore.ieee.org
Currently, most face anti-spoofing methods target the generalization problem by relying on
auxiliary information such as additional annotations and modalities. However, this auxiliary …

DFIE3D: 3D-Aware Disentangled Face Inversion and Editing Via Facial-contrastive Learning

X Zhu, J Zhou, L You, X Yang, J Chang… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Recent advances in NeRF-based 3D-aware GANs have achieved outstanding performance,
especially in the realm of human facial representations, making projection of facial images …

Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics

M Fang, N Damer - Proceedings of the IEEE/CVF Winter …, 2024 - openaccess.thecvf.com
Recent face presentation attack detection (PAD) leverages domain adaptation (DA) and
domain generalization (DG) techniques to address performance degradation on unknown …