Sorry, you need to enable JavaScript to visit this website.

Although many deepfake detection methods have been proposed to fight against severe misuse of generative AI, none provide detailed human-interpretable explanations beyond simple real/fake responses. This limitation makes it challenging for humans to assess the accuracy of detection results, especially when the models encounter unseen deepfakes. To address this issue, we propose a novel deepfake detector based on a large Vision-Language Model (VLM), capable of explaining manipulated facial regions.

Pre-trained large foundation models play a central role in the recent surge of artificial intelligence, resulting in fine-tuned models with remarkable abilities when measured on benchmark datasets, standard exams, and applications. Due to their inherent complexity, these models are not well understood; in particular, the structures of the representation space are not well characterized despite their fundamental importance. In this paper,

supplementary material

Supp for our ICIP submission: ROLLOUT-GUIDED TOKEN PRUNING FOR EFFICIENT VIDEO UNDERSTANDING

This 2-page document provides supplementary material for the paper titled "Perceptual Classifiers for Detecting Generative Images". It provides details on the datasets used and their composition. We also include the real and fake detection accuracies for each class to help readers better understand the strengths and drawbacks of the proposed approach. Finally, we provide t-SNE visualizations to understand the effectiveness of the chosen feature extractors.

In this supplementary material for "SCIGS: 3D GAUSSIANS SPLATTING FROM A SNAPSHOT COMPRESSIVE IMAGE", the results of comparative experiments on all the datasets from dynamic scenes and static scenes are shown. The experiment compares our SCIGS against current state-of-the-art SCI decoding methods and state-of-the-art SCI image-based reconstruction method. An additional experiment is conducted to assess the impact of various mask overlapping rates during the SCI image modulated.

Supplementary Materials for "WEAKLY SUPERVISED DEFECT LOCALIZATION WITH RESIDUAL FEATURES"

Accurate 3D modeling of humans and high-fidelity garments is crucial in computer vision and graphics, impacting gaming, virtual, and augmented reality applications.

Facial Expression Recognition (FER) has achieved significant success in recent years due to the rise of deep learning. Meanwhile, latent semantic information is crucial for recognizing facial expressions with subtle differences. Inspired by inconsistencies in learning intensity across different layers of deep learning networks — where shallow-layer features lack generalization and task relevance compared to deep-layer features — we propose a novel Hierarchical Semantic Transfer (HST) method.

Facial Expression Recognition (FER) has achieved significant success in recent years due to the rise of deep learning. Meanwhile, latent semantic information is crucial for recognizing facial expressions with subtle differences. Inspired by inconsistencies in learning intensity across different layers of deep learning networks — where shallow-layer features lack generalization and task relevance compared to deep-layer features — we propose a novel Hierarchical Semantic Transfer (HST) method.