Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Alex Chichung KotSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works35 from public data
- DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing97
This work proposes a novel framework based on the Convolutional Neural Network and the Recurrent Neural Network to solve the face anti-spoofing problem and introduces a recurrent mechanism to learn representations of local information sequentially from the explored sub-patches with an RNN.
- Learning Meta Pattern for Face Anti-Spoofing92
A learnable network to extract Meta Pattern (MP) and a two-stream network to hierarchically fuse the input RGB image and the extracted MP by using the proposed Hierarchical Fusion Module (HFM) are proposed.
- Benchmarking Joint Face Spoofing and Forgery Detection With Visual and Physiological Cues74
The first joint face spoofing and forgery detection benchmark using both visual appearance and physiological rPPG cues is established and it is found that the generalization capacities of both unimodal (appearance or rPPG) and multi-modal (appearance+rPPG) models can be obviously improved via joint training on these two tasks.
- Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing74
The modality-asymmetric masked autoencoder is proposed for multimodal FAS self-supervised pre-training without costly annotated labels and is able to learn more intrinsic task-aware representation and compatible with modality-agnostic downstream settings.
- S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing With Statistical Tokens46
A generalized FAS method under the Efficient Parameter Transfer Learning (EPTL) paradigm, where the pre-trained Vision Transformer models are adapted for the FAS task, and a novel Statistical Adapter (S-Adapter) that gathers local discriminative and statistical information from localized token histograms is proposed.
- 41
- 40
- Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing38
The Uncertainty-Guided Cross-Adapter (U-Adapter) is proposed to recognize unreliably detected regions within each modality and suppress the impact of unreliable regions on other modal-ities, and a Rebalanced Modality Gradient Modulation (ReGrad) strategy to rebal-ance the convergence speed of all modalities by adaptively adjusting their gradients is proposed.
- Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less36
This paper proposes the first rehearsal-free method for Domain Continual Learning of FAS, which deals with catastrophic forgetting and unseen domain generalization problems simultaneously and proposes the Proxy Prototype Contrastive Regularization (PPCR) to constrain the continual learning with previous domain knowledge from the proxy prototypes.
- 33
- Towards Data-Centric Face Anti-spoofing: Improving Cross-Domain Generalization via Physics-Based Data Synthesis31
This work proposes task-specific FAS data augmentation (FAS-Aug), which increases data diversity by synthesizing data of artifacts, such as printing noise, color distortion, moiré pattern, etc, and proposes Spoofing Attack Risk Equalization (SARE) to prevent models from relying on certain types of artifacts and improve the generalization performance.
- Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme28
A Task-Driven Cropping scheme, dubbed TDC, for improving the deep image detection algorithms towards efficient and effective luggage inspection via X-ray images, which shows that the proposed TDC algorithm can effectively boost popular detection algorithms, by achieving better detection mAPs or reducing the run time.
- 27
- 21
- 17
- 15
- 13
- Visual Prompt Flexible-Modal Face Anti-Spoofing11
Inspired by the recent success of the prompt learning in language models, Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task, is proposed.
- Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters11
This paper sets up a Generalized FSCL (GFSCL) protocol involving both class- and domain-incremental situations together with the domain generalization assessment, and proposes a rehearsal-free framework based on Vision Transformer named Contrastive Mixture of Adapters (CMoA).
- 10
- 9
- 8
- Hyperbolic Face Anti-Spoofing6
This work proposes to learn richer hierarchical and discriminative spoofing cues in hyperbolic space, and designs a multimodal FAS framework with Euclidean multi-modal feature decomposition andhyperbolic multimodals feature fusion&classification.
- Evaluating the efficacy of skincare product: A realistic short-term facial pore simulation5
The proposed simulation is able to render realistic facial pore changes and will pave the way for future research in facial skin simulation and skincare product developments.
- Image Inpainting Detection via Enriched Attentive Pattern with Near Original Image Augmentation5
This work proposes near original image augmentation that pushes the inpainted images closer to the original ones (without distortion and inpainting) as the input images, which is proved to improve the detection accuracy.
- ContextualCoder: Adaptive In-Context Prompting for Programmatic Visual Question Answering3
This paper proposes ContextualCoder, a novel prompting framework tailored for PVQA models that surpasses state-of-the-art models and facilitates the use of diverse in-context information for code generation, thereby improving the performance of PVQA models.
- 3
- Toward domain generalized pruning by scoring out-of-distribution importance3
This work designs the importance scoring estimation by using the variance of domain-level risks to consider the pruning risk in the unseen distribution and shows that under the same pruning ratio, the method can achieve significantly better cross-domain generalization performance than the baseline filter pruning method.
- AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution2
This work is the first study to explore skin assessment from selfie facial images without physical measurements, enabling AI-driven accessible skin analysis for broader real-world applications.
- PS-Net: high-frequency attention and Bayesian analysis based facial pore segmentation with no human annotation2
A novel method called the pore segmentation network (PS-Net), which contains pore feature extraction with coarse labels generated by a traditional method, as well as fine segmentation with progressively updated pseudo labels, and designs a Bayesian module to identify pore shapes in high-level features.
- Learning deep forest for face anti-spoofing: An alternative to the neural network against adversarial attacks2
A novel solution for FAS against adversarial attacks, leveraging a deep forest model based on local binary patterns (LBP) as the model input, replacing the grained-scanning mechanism used in the traditional deep forest model.
- Controllable and Gradual Facial Blemishes Retouching Via Physics-Based Modelling1
The CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space, and shows that CGFR can realistically simulate the blemishes’ gradual recovering process.
- Forensicability Assessment of Questioned Images in Recapturing Detection1
This is the first work that assesses the forensicability of recaptured document images and improves the system efficiency, and proposes a forensicability assessment network to quantify the forensicability of the questioned samples.
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.