SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4465-4474
Abstract
No abstract availableFunding Information
- NSFC (62232006)
- NSFC (62522206)
- NSFC (62521004)
This publication has 21 references indexed in Scilit:
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models2025
- Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection2025
- Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning2025
- Temporal surface frame anomalies for deepfake video detection2024
- Beyond Deepfake Images: Detecting AI-Generated Videos2024
- Exploiting Style Latent Flows for Generalizing Deepfake Video Detection2024
- AltFreezing for More General Video Face Forgery Detection2023
- Protecting Celebrities from DeepFake with Identity Consistency Transformer2022
- Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection2021
- SphereFace: Deep Hypersphere Embedding for Face Recognition2017