149 citations · 194 across the 26 of their papers we have counts for
32 papers
PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents
Hanzhong Zhang, Ziwei Xiang, Weicheng Xie +2
The profile of a role-playing agent usually depends on the pre-defined personality in a system prompt, whereas its memory processing pipeline, including prioritisation of stored me…
Conversational Human Audio-visual Talking Dialogue Generation
Junhao Song, Lluis Guasch, Xilin He +8
Large-scale dyadic interactive audio-visual dialogue (DIAD) datasets provide fundamental data resources for developing humanoid interactive virtual agents and digital humans. Howev…
Text-Guided Multimodal Unified Industrial Anomaly Detection
Zewen Li, Shuo Ye, Zitong Yu +2
Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer…
Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
Zenghao Niu, Weicheng Xie, Siyang Song +3
Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transfer…
IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection
Zewen Li, Zitong Yu, Qilang Ye +3
The robust causal capability of Multimodal Large Language Models (MLLMs) hold the potential of detecting defective objects in Industrial Anomaly Detection (IAD). However, most trad…
SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning
Xiaole Xian, Zhichao Liao, Qingyu Li +6
Fine-tuning a pre-trained Text-to-Image (T2I) model on a tailored portrait dataset is the mainstream method for text-to-portrait customization. However, existing methods often seve…
Oral Imaging for Malocclusion Issues Assessments: OMNI Dataset, Deep Learning Baselines and Benchmarking
Pujun Xue, Junyi Ge, Xiaotong Jiang +8
Malocclusion is a major challenge in orthodontics, and its complex presentation and diverse clinical manifestations make accurate localization and diagnosis particularly important.…
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…
PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing
Yiping Xie, Bo Zhao, Mingtong Dai +6
Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains highly susceptible to illumination changes, motion artifacts, and limited temporal mode…
Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification
Wennuo Yang, Shiling Wu, Yuzhi Zhou +5
Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from heal…
DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis
Kaijun Deng, Dezhi Zheng, Jindong Xie +4
Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existi…
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…
CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing
Xiaole Xian, Xilin He, Zenghao Niu +5
For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional fine-tuning for different editing effects or tend to affect…
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Xilin He, Jingyu Hu, Qinliang Lin +5
Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks fr…
SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data
Xilin He, Cheng Luo, Xiaole Xian +8
Facial expression datasets remain limited in scale due to the subjectivity of annotations and the labor-intensive nature of data collection. This limitation poses a significant cha…
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency
Yiping Xie, Zitong Yu, Bingjie Wu +2
Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG m…
Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition
Zihan Wang, Siyang Song, Cheng Luo +3
Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs loc…
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
Qinliang Lin, Cheng Luo, Zenghao Niu +5
Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement a…
Joint Prediction of Audio Event and Annoyance Rating in an Urban Soundscape by Hierarchical Graph Representation Learning
Yuanbo Hou, Siyang Song, Cheng Luo +6
Sound events in daily life carry rich information about the objective world. The composition of these sounds affects the mood of people in a soundscape. Most previous approaches on…
MRecGen: Multimodal Appropriate Reaction Generator
Jiaqi Xu, Cheng Luo, Weicheng Xie +5
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour. This paper proposes the fir…
ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions
Cheng Luo, Siyang Song, Weicheng Xie +4
In dyadic interaction, predicting the listener's facial reactions is challenging as different reactions could be appropriate in response to the same speaker's behaviour. Previous a…
Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection
Zihan Wang, Siyang Song, Cheng Luo +4
This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main…
GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features
Siyang Song, Yuxin Song, Cheng Luo +7
Graph is powerful for representing various types of real-world data. The topology (edges' presence) and edges' features of a graph decides the message passing mechanism among verti…
Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator
Xiangbo Gao, Cheng Luo, Qinliang Lin +5
\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms. Recent CNN gene…