4 citations · 13 across the 18 of their papers we have counts for
21 papers
Forensic-Aware Continual Adaptation for Image Forgery Localization
Chenqi Kong, Song Xia, Anwei Luo +3
The rapid evolution of image manipulation techniques has raised growing public security concerns. Existing Image Forgery Localization (IFL) methods can accurately localize manipula…
FVeinSyn: Synthetic Finger Vein Image Generator
Yifan Wang, Jie Gui, Adams Wai Kin Kong +6
A major challenge in finger vein recognition is the lack of large-scale public datasets. Existing datasets contain few identities and limited samples per finger, restricting the ad…
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations
Weichen Liu, Yixin Yang, Changsheng Chen +1
Suspect face generation remains a technical challenge in crime investigations. Traditional sketch-drawing workflows suffer from low efficiency and quality, while diffusion-based ap…
Learning Representation and Synergy Invariances: A Povable Framework for Generalized Multimodal Face Anti-Spoofing
Xun Lin, Shuai Wang, Yi Yu +6
Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in un…
AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution
Cecelia Soh, Rizhao Cai, Monalisha Paul +2
Skin health and disease resistance are closely linked to the skin barrier function, which protects against environmental factors and water loss. Two key physiological indicators ca…
ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
Rongxuan Peng, Shunquan Tan, Chenqi Kong +3
Parameter-efficient fine-tuning (PEFT) has emerged as a popular strategy for adapting large vision foundation models, such as the Segment Anything Model (SAM) and LLaVA, to downstr…
Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation
Yi Yu, Song Xia, Xun Lin +5
Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these exa…
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
Yi Yu, Song Xia, Xun Lin +4
No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and o…
Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis
Rizhao Cai, Cecelia Soh, Zitong Yu +3
Face Anti-Spoofing (FAS) research is challenged by the cross-domain problem, where there is a domain gap between the training and testing data. While recent FAS works are mainly mo…
Towards Physical World Backdoor Attacks against Skeleton Action Recognition
Qichen Zheng, Yi Yu, Siyuan Yang +3
Skeleton Action Recognition (SAR) has attracted significant interest for its efficient representation of the human skeletal structure. Despite its advancements, recent studies have…
Semantic Deep Hiding for Robust Unlearnable Examples
Ruohan Meng, Chenyu Yi, Yi Yu +3
Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from u…
Controllable and Gradual Facial Blemishes Retouching via Physics-Based Modelling
Chenhao Shuai, Rizhao Cai, Bandara Dissanayake +5
Face retouching aims to remove facial blemishes, such as pigmentation and acne, and still retain fine-grain texture details. Nevertheless, existing methods just remove the blemishe…
Benchmarking Cross-Domain Audio-Visual Deception Detection
Xiaobao Guo, Zitong Yu, Nithish Muthuchamy Selvaraj +3
Automated deception detection is crucial for assisting humans in accurately assessing truthfulness and identifying deceptive behavior. Conventional contact-based techniques, like p…
Improving Concept Alignment in Vision-Language Concept Bottleneck Models
Nithish Muthuchamy Selvaraj, Xiaobao Guo, Adams Wai-Kin Kong +1
Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language…
MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
Chenqi Kong, Anwei Luo, Peijun Bao +5
Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expr…
Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations
Xun Lin, Yi Yu, Song Xia +8
The widespread availability of publicly accessible medical images has significantly propelled advancements in various research and clinical fields. Nonetheless, concerns regarding…
Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
Xun Lin, Shuai Wang, Rizhao Cai +5
Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks. With advancements in sensor manufacture and multi-modal learning techniques,…
MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition
Fan Zhang, Xiaobao Guo, Xiaojiang Peng +1
Cutting-edge research in facial expression recognition (FER) currently favors the utilization of convolutional neural networks (CNNs) backbone which is supervisedly pre-trained on…
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…
Pixel-Inconsistency Modeling for Image Manipulation Localization
Chenqi Kong, Anwei Luo, Shiqi Wang +3
Digital image forensics plays a crucial role in image authentication and manipulation localization. Despite the progress powered by deep neural networks, existing forgery localizat…
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…