Publications (41)
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…
Dynamic Analysis and Adaptive Discriminator for Fake News Detection
Xinqi Su, Zitong Yu, Yawen Cui +7
In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection methods can generall…
A Distributed Approach towards Discriminative Distance Metric Learning
Jun Li, Xun Lin, Xiaoguang Rui +2
Distance metric learning is successful in discovering intrinsic relations in data. However, most algorithms are computationally demanding when the problem size becomes large. In th…
Fully faithful functors, skyscraper sheaves, and birational equivalence
Chunyi Li, Xun Lin, Xiaolei Zhao
Let and be two smooth projective varieties such that there is a fully faithful exact functor from to . We show that and …
FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models
Hongyang Wang, Yichen Shi, Zhuofu Tao +7
Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking…
TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation
Jiale Zhou, Wenhan Wang, Shikun Li +6
Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts re…
VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation
Zhipeng Deng, Jiale Zhou, Wenhan Jiang +4
Deploying multi-sequence magnetic resonance imaging (MRI) segmentation models to new clinical environments is challenging due to variations in scanners and acquisition protocols. A…
Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
Yi Yu, Qixin Zhang, Shuhan Ye +6
Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We st…
Infinitesimal Torelli problems for special Gushel-Mukai and related Fano threefolds: Hodge theoretical and categorical perspectives
Xun Lin, Shizhuo Zhang, Zheng Zhang
We investigate infinitesimal Torelli problems for some of the Fano threefolds of the following two types: (a) those which can be described as zero loci of sections of vector bundle…
DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models
Jing Yang, Runping Xi, Yingxin Lai +2
Diffusion-based personalized visual content generation technologies have achieved significant breakthroughs, allowing for the creation of specific objects by just learning from a f…
AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering
Jiayu Zhang, Shuo Ye, Qilang Ye +3
Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse questions about audio-visual scenes.…
Transferable Adversarial Attacks on SAM and Its Downstream Models
Song Xia, Wenhan Yang, Yi Yu +4
The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical…
Noncommutative Hodge conjecture
Xun Lin
The paper provides a version of the rational Hodge conjecture for $\3\dg$ categories. The noncommutative Hodge conjecture is equivalent to the version proposed in \cite{perry2020in…
Some remarks of Hochschild homology and semi-orthogonal decompositions
Xun Lin
Given a nontrivial semi-orthogonal decomposition $\Perf(\X)=\langle \mathcal{A},\mathcal{B}\rangle$, and assume that the base locus of $Ï_{\X}$ is a proper closed subset, it was p…
VoxShield: Protecting 3D Medical Datasets from Unauthorized Training via Frequency-Aware Inter-Slice Disruption
Xinyao Liu, Zhipeng Deng, Wenhan Jiang +4
The release of public 3D medical image segmentation (MIS) datasets accelerates clinical research but simultaneously heightens risks of unauthorized AI model training. While Unlearn…
StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
Lixin Chen, Chaomeng Chen, Jiale Zhou +2
Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privac…
DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing
Jingyi Yang, Xun Lin, Zitong Yu +5
With the availability of diverse sensor modalities (i.e., RGB, Depth, Infrared) and the success of multi-modal learning, multi-modal face anti-spoofing (FAS) has emerged as a promi…
Serre algebra, matrix factorization and categorical Torelli theorem for hypersurfaces
Xun Lin, Shizhuo Zhang
Let be a smooth Fano variety. We attach a bi-graded associative algebra $\mathrm{HS}(\mathcal{K}u(X))=\bigoplus_{i,j\in \mathbb{Z}} \mathrm{Hom}(\mathrm{Id},S_{\mathcal{K}u(X)}…
Indecomposability of the bounded derived categories of Brill-Noether varieties
Xun Lin, Chenglong Yu
We prove that the bounded derived category of coherent sheaves of the Brill-Noether variety that parametrizing linear series of degree and dimension on a gen…
Semiorthogonal indecomposability for Hilbert schemes of points on integral locally planar curves
Qingyuan Jiang, Xun Lin
Let be an integral projective curve of arithmetic genus with locally planar singularities over an algebraically closed field. We prove that for every , bot…
SVC 2026: the Second Multimodal Deception Detection Challenge and the First Domain Generalized Remote Physiological Measurement Challenge
Dongliang Zhu, Zhiyi Niu, Bo Zhao +14
Subtle visual signals, although difficult to perceive with the naked eye, contain important information that can reveal hidden patterns in visual data. These signals play a key rol…
EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities
Zhe Chen, Xun Lin, Yawen Cui +1
Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities…
On nonexistence of semi-orthogonal decompositions in algebraic geometry
Xun Lin
The nonexistence of semi-orthogonal decompositions in algebraic geometry is known to be governed by the base locus of the canonical bundle. We study another locus, namely the inter…
Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing
Yingjie Ma, Xun Lin, Zitong Yu +7
Face Anti-Spoofing (FAS) is essential for the security of facial recognition systems in diverse scenarios such as payment processing and surveillance. Current multimodal FAS method…
IVHS via Kuznetsov components and categorical Torelli theorems for weighted hypersurfaces
Xun Lin, Jørgen Vold Rennemo, Shizhuo Zhang
We study the categorical Torelli theorem for smooth (weighted) hypersurfaces in (weighted) projective spaces via the Hochschild--Serre algebra of its Kuznetsov component. In the fi…
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…
Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement
Xun Lin, Wenzhong Tang, Haoran Wang +4
Recently, a surge in scientific publications suspected of image manipulation has led to numerous retractions, bringing the issue of image integrity into sharp focus. Although resea…
BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
Yingjie Ma, Zitong Yu, Xun Lin +2
In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challen…
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,…
MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
Qian Wu, Xinrong Zhou, Zizhan Ma +8
Large Language Models (LLMs) show promise for medical education, but most existing systems focus on localized interactions such as question answering or single-turn feedback, rathe…
Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification
Jiayang Wu, Jiale Zhou, Rubo Wang +5
Accurate identification of protein active sites at the residue level is crucial for understanding protein function and advancing drug discovery. However, current methods face two c…
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…
SVC 2025: the First Multimodal Deception Detection Challenge
Xun Lin, Xiaobao Guo, Taorui Wang +5
Deception detection is a critical task in real-world applications such as security screening, fraud prevention, and credibility assessment. While deep learning methods have shown p…
AdaMHF: Adaptive Multimodal Hierarchical Fusion for Survival Prediction
Shuaiyu Zhang, Xun Lin, Rongxiang Zhang +5
The integration of pathologic images and genomic data for survival analysis has gained increasing attention with advances in multimodal learning. However, current methods often ign…
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…
StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
Guoqing Ma, Xun Lin, Hui Ma +6
Most existing Face Forgery Detection (FFD) models assume access to raw face images. In practice, under a client-server framework, private facial data may be intercepted during tran…
Three approaches to a categorical Torelli theorem for cubic threefolds of non-Eckardt type via the equivariant Kuznetsov components
Sebastian Casalaina-Martin, Xianyu Hu, Xun Lin +2
Let be a cubic threefold with a non-Eckardt type involution . Our first main result is that the -equivariant category of the Kuznetsov component $\mathcal{K}u_{\mathbb{…
Infinitesimal categorical Torelli theorems for Fano threefolds
Augustinas Jacovskis, Xun Lin, Zhiyu Liu +1
Let be a smooth Fano variety and the Kuznetsov component. Torelli theorems for says that it is uniquely determined by a polarized abelian va…
Kuznetsov's Fano threefold conjecture via Hochschild-Serre algebra
Xun Lin, Shizhuo Zhang
Let be a smooth quartic double solid regarded as a degree 4 hypersurface of the weighted projective space . We study the multiplication of Hochschild-Ser…
PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning
Yingjie Ma, Xun Lin, Yong Xu +2
Face anti-spoofing (FAS) has recently advanced in multimodal fusion, cross-domain generalization, and interpretability. With large language models and reinforcement learning (RL),…
Categorical Torelli theorems for Gushel-Mukai threefolds
Augustinas Jacovskis, Xun Lin, Zhiyu Liu +1
We show that a general ordinary Gushel-Mukai(GM) threefold is reconstructed from the Kuznetsov component together with an extra data coming from tautological…