相关论文: Adaptive Forensic Feature Refinement via Intrinsic…

Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final layer, we systematically analyze the contributions of…

Self-supervised learning is emerging in fine-grained visual recognition with promising results. However, existing self-supervised learning methods are often susceptible to irrelevant patterns in self-supervised tasks and lack the capability…

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two…

Synthetic face recognition (SFR) aims to generate synthetic face datasets that mimic the distribution of real face data, which allows for training face recognition models in a privacy-preserving manner. Despite the remarkable potential of…

Deepfake detection methods have shown promising results in recognizing forgeries within a given dataset, where training and testing take place on the in-distribution dataset. However, their performance deteriorates significantly when…

Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suffer from "semantic blindness," leading to the erroneous…

Current object re-identification (ReID) methods train domain-specific models (e.g., for persons or vehicles), which lack generalization and demand costly labeled data for new categories. While self-supervised learning reduces annotation…

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision…

We propose Filtering Inversion (FINV), a learning framework and optimization process that predicts a renderable 3D object representation from one or few partial views. FINV addresses the challenge of synthesizing novel views of objects from…

Image feature matching is to seek, localize and identify the similarities across the images. The matched local features between different images can indicate the similarities of their content. Resilience of image feature matching to large…

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. Though DIP inversion has been known to be superior to…

Multimodal deepfake detection (MDD) aims to uncover manipulations across visual, textual, and auditory modalities, thereby reinforcing the reliability of modern information systems. Although large vision-language models (LVLMs) exhibit…

This research focuses on the discovery and localization of hidden objects in the wild and serves unmanned systems. Through empirical analysis, infrared and visible image fusion (IVIF) enables hard-to-find objects apparent, whereas…

Recently, generated images could reach very high quality, even human eyes could not tell them apart from real images. Although there are already some methods for detecting generated images in current forensic community, most of these…

As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a…

This paper tackles the challenge of detecting partially manipulated facial deepfakes, which involve subtle alterations to specific facial features while retaining the overall context, posing a greater detection difficulty than fully…

This paper introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data. It is based on the DPOD detector, which produces dense 2D-3D correspondences between the model vertices…

Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands…

Training large language models (LLMs) efficiently while preserving model quality poses significant challenges, particularly with subbyte precision supported by state-of-the-art GPUs. Current mixed-precision training approaches either apply…