Related papers: UniShield: Unified Face Attack Detection via KG-In…

Tuning-free face personalization methods have developed along two distinct paradigms: text embedding approaches that map facial features into the text embedding space, and adapter-based methods that inject features through auxiliary…

Large language models (LLMs) exhibit pronounced social biases. Output-level or data-optimization--based debiasing methods cannot fully resolve these biases, and many prior works have shown that biases are embedded in internal…

We propose an adversarial attack for facial class-specific Single Image Super-Resolution (SISR) methods. Existing attacks, such as the Fast Gradient Sign Method (FGSM) or the Projected Gradient Descent (PGD) method, are either fast but…

Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of…

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering…

Face recognition (FR) algorithms have been proven to exhibit discriminatory behaviors against certain demographic and non-demographic groups, raising ethical and legal concerns regarding their deployment in real-world scenarios. Despite the…

The paper addresses face presentation attack detection in the challenging conditions of an unseen attack scenario where the system is exposed to novel presentation attacks that were not present in the training step. For this purpose, a pure…

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor…

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…

Recent face presentation attack detection (PAD) leverages domain adaptation (DA) and domain generalization (DG) techniques to address performance degradation on unknown domains. However, DA-based PAD methods require access to unlabeled…

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…

Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases. In this work, we introduce \textit{Poisoned-MRAG},…

Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models excel within single modalities, they suffer from substantial cross-modal degradation, an issue…

The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods. Existing solutions primarily address unimodal (audio or visual) forgeries but struggle with multimodal…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with breaking news. Recent…

Multi-modal object Re-IDentification (ReID) has gained considerable attention with the goal of retrieving specific targets across cameras using heterogeneous visual data sources. At present, multi-modal object ReID faces two core…

The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible…

Deep reinforcement learning (DRL) is widely applied to safety-critical decision-making scenarios. However, DRL is vulnerable to backdoor attacks, especially action-level backdoors, which pose significant threats through precise manipulation…

Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented -- focusing on either text or images in…