Search Results for author:
Found 18 papers, 6 papers with code
Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks.
BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles.
Ranked #1000000000 on
Visual Question Answering
on MS COCO
Forgery-aware Adaptive Vision Transformer for Face Forgery Detection
To circumvent these issues, we propose a novel Forgery-aware Adaptive Vision Transformer (FA-ViT).
S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition system by presenting spoofed faces.
Hyperbolic Face Anti-Spoofing
To further improve generalization, we conduct hyperbolic contrastive learning for the bonafide only while relaxing the constraints on diverse spoofing attacks.
Visual Prompt Flexible-Modal Face Anti-Spoofing
Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems.
Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
To alleviate the forgetting of previous domains without using previous data, we propose the Proxy Prototype Contrastive Regularization (PPCR) to constrain the continual learning with previous domain knowledge from the proxy prototypes.
Evaluating the Efficacy of Skincare Product: A Realistic Short-Term Facial Pore Simulation
In this paper, we propose the first simulation model to reveal facial pore changes after using skincare products.
Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.
Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
In this paper, we investigate three key factors (i. e., inputs, pre-training, and finetuning) in ViT for multimodal FAS with RGB, Infrared (IR), and Depth.
Toward domain generalized pruning by scoring out-of-distribution importance
Filter pruning has been widely used for compressing convolutional neural networks to reduce computation costs during the deployment stage.
Forensicability Assessment of Questioned Images in Recapturing Detection
We integrate the trained FANet with practical recapturing detection schemes in face anti-spoofing and recaptured document detection tasks.
Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues
In this paper, we establish the first joint face spoofing and forgery detection benchmark using both visual appearance and physiological rPPG cues.
One-Class Knowledge Distillation for Face Presentation Attack Detection
Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD.
Automatic Facial Skin Feature Detection for Everyone
We present an automatic facial skin feature detection method that works across a variety of skin tones and age groups for selfies in the wild.
Learning Meta Pattern for Face Anti-Spoofing
To improve the generalization ability, recent hybrid methods have been explored to extract task-aware handcrafted features (e. g., Local Binary Pattern) as discriminative information for the input of DNNs.
DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing
Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i. e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative information, for the face anti-spoofing problem, we propose a novel framework based on the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN).
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing
Studies about the transferability of the adversarial attack reveal that utilizing handcrafted feature-based methods could improve security in a system-level.
