相关论文: Visual Prompt Flexible-Modal Face Anti-Spoofing

Multimodal tasks in the fashion domain have significant potential for e-commerce, but involve challenging vision-and-language learning problems - e.g., retrieving a fashion item given a reference image plus text feedback from a user. Prior…

Face recognition technology has become an integral part of modern security systems and user authentication processes. However, these systems are vulnerable to spoofing attacks and can easily be circumvented. Most prior research in face…

Multimodal models often experience a significant performance drop when one or more modalities are missing during inference. To address this challenge, we propose a simple yet effective approach that enhances robustness to missing modalities…

Ensuring fairness across demographic groups in medical diagnosis is essential for equitable healthcare, particularly under distribution shifts caused by variations in imaging equipment and clinical practice. Vision-language models (VLMs)…

Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations. Nonetheless, for downstream inference, CLIP-like models suffer from either 1) degraded accuracy and…

Face-swapping models have been drawing attention for their compelling generation quality, but their complex architectures and loss functions often require careful tuning for successful training. We propose a new face-swapping model called…

Current RGBT tracking research relies on the complete multi-modal input, but modal information might miss due to some factors such as thermal sensor self-calibration and data transmission error, called modality-missing challenge in this…

Multimodal data collected from the real world are often imperfect due to missing modalities. Therefore multimodal models that are robust against modal-incomplete data are highly preferred. Recently, Transformer models have shown great…

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple…

Nowadays, we have witnessed the early progress on learning the association between voice and face automatically, which brings a new wave of studies to the computer vision community. However, most of the prior arts along this line (a) merely…

Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under illumination and pose variations. Recently several low-rank…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image…

We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the…

Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered…

In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed, pre-trained model at testing time. Compared to conventional adversarial defenses, VP allows us to design universal (i.e., data-agnostic) input…

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either…

Multimodal physiological signals, such as EEG, ECG, EOG, and EMG, are crucial for healthcare and brain-computer interfaces. While existing methods rely on specialized architectures and dataset-specific fusion strategies, they struggle to…

Although vision-language pre-training (VLP) models have achieved remarkable progress on cross-modal tasks, they remain vulnerable to adversarial attacks. Using data augmentation and cross-modal interactions to generate transferable…

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 deep learning models but their cross-domain generalization…