CORTEXA
← Browse
arxivcs.CV2026-07-23

DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing

Pierre Gallin-Martel, Mika Feng, Koichi Ito, Takafumi Aoki

With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs) demonstrate high generalization in this context, they heavily rely on complex multimodal fusion and external text encoders. In this paper, we propose DINO-VPT, a lightweight, vision-only framework leveraging hierarchical visual prompt tuning. By dynamically injecting prompts conditioned on input features via a Prompt Routing Network (PRN), our method effectively disentangles diverse spoofing artifacts without requiring multimodal fusion. Evaluations on the UniAttackData benchmark demonstrate that DINO-VPT achieves higher accuracy than state-of-the-art VLM-based methods. Our results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.

View free PDFSource page

Related papers

arxivcs.CV2026-07-06

Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising

Guangting Zheng, Haojing Chen, Hao Li, Jingtao Zhang, Zhen Yang, Xiaosong Jia, et al.

While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene.…

View free PDFSource page
arxiveess.IVcs.AIcs.CV2026-07-15

ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model

San Lee, Nalee Kim, Jeong Il Yu, Hee Chul Park, Boah Kim

In proton therapy planning, respiratory-gated non-contrast CT (NCCT) is commonly used for lesion segmentation; however, accurate delineation remains challenging due to low lesion-to-background contrast. Although learning-based methods have shown strong performance, they often str…

View free PDFSource page
arxivcs.CV2026-07-23

Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach

Yuhua Wang, Xiaodong Li, Yihao Guo, Yuxiang Jia, Qinnan Zhang, Yifan Sun, et al.

Federated prompt tuning (FPT) enables collaborative adaptation of vision--language models (VLMs) using lightweight prompts. Existing methods often address heterogeneity and privacy through a split-prompt design under local differential privacy (DP), combining a shared prompt for…

View free PDFSource page
arxivcs.CV2026-07-07

Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition

Xinda Liu, Qinyu Zhang, Weiqing Min, Guohua Geng, Shuqiang Jiang

Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language models (VLMs) like CLIP provide a compelling zero-shot alternative, reducing reliance on extensive labeled data. However, their…

View free PDFSource page
arxivcs.CV2026-07-01

Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

Yeonghwan Song, Chanhui Lee, Jinsoo Park, Jeany Son

Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image,…

View free PDFSource page
arxivcs.CV2026-07-16

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

Yinhan Zhang, Dingwei Tan, Xianghao Kong, Yue Ma, Yeying Jin, Anyi Rao

Large-scale video diffusion models deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require…

View free PDFSource page