98 citations · 235 across the 21 of their papers we have counts for
9 papers · 1 filter
BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
Rizhao Cai, Zirui Song, Dayan Guan +4
Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles. However, their robustness against diverse s…
Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer
Anwei Luo, Rizhao Cai, Chenqi Kong +4
With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains…
S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Rizhao Cai, Zitong Yu, Chenqi Kong +4
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 de…
Hyperbolic Face Anti-Spoofing
Shuangpeng Han, Rizhao Cai, Yawen Cui +3
Learning generalized face anti-spoofing (FAS) models against presentation attacks is essential for the security of face recognition systems. Previous FAS methods usually encourage…
Visual Prompt Flexible-Modal Face Anti-Spoofing
Zitong Yu, Rizhao Cai, Yawen Cui +2
Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data colle…
Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
Rizhao Cai, Yawen Cui, Zhi Li +4
Face Anti-Spoofing (FAS) is recently studied under the continual learning setting, where the FAS models are expected to evolve after encountering the data from new domains. However…
Evaluating the Efficacy of Skincare Product: A Realistic Short-Term Facial Pore Simulation
Ling Li, Bandara Dissanayake, Tatsuya Omotezako +8
Simulating the effects of skincare products on face is a potential new way to communicate the efficacy of skincare products in skin diagnostics and product recommendations. Further…
Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters
Yawen Cui, Zitong Yu, Rizhao Cai +3
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 F…
Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Zitong Yu, Rizhao Cai, Yawen Cui +3
Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no w…