SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
- URL: http://arxiv.org/abs/2608.01334v1
- Date: Sun, 02 Aug 2026 15:54:54 GMT
- Title: SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
- Abstract summary: AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones.<n>In practice, detectors trained on existing data often fail to generalize to newly emerging generative models.<n>We propose SphereVideo, a novel framework for AIGV detection built on two key observations.
- Score: 61.05420454815012
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones. In practice, detectors trained on existing data often fail to generalize to newly emerging generative models, making this task challenging. Therefore, continual learning (CL) is essential for improving the adaptability. However, CL frameworks for this task remain underexplored. To this end, we propose SphereVideo, a novel CL framework for AIGV detection built on two key observations. First, real videos exhibit a compact feature distribution. Based on this, we encourage real video features to cluster around a real prototype on a hypersphere while repelling AI-generated samples, thereby establishing a decision boundary. This prototype serves as a stable anchor for CL, regulating boundary evolution and mitigating catastrophic forgetting. Second, existing methods tend to rely solely on spatial artifacts as shortcuts. To enhance temporal modeling, we introduce a strategy that models the temporal dynamics of real data at both frame and clip levels. By strengthening real data modeling, this strategy further facilitates learning a real prototype and forming a stable decision boundary. Moreover, we construct a comprehensive and challenging benchmark. Extensive experiments demonstrate that SphereVideo achieves an improved plasticity-stability trade-off, outperforming prior methods by 3.08% on seen data and 4.00% on unseen AI-generated data.
Related papers
- Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale [36.51885181895111]
We introduce a comprehensive dataset and a novel detection framework.<n>First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators.<n>We propose a novel detection framework built on the Qwen-VL Vision Transformer, which operates at variable spatial resolutions and temporal durations.
arXiv Detail & Related papers (2026-04-06T12:36:08Z) - Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
arXiv Detail & Related papers (2025-10-27T03:52:45Z) - Leveraging Pre-Trained Visual Models for AI-Generated Video Detection [54.88903878778194]
The field of video generation has advanced beyond DeepFakes, creating an urgent need for methods capable of detecting AI-generated videos with generic content.<n>We propose a novel approach that leverages pre-trained visual models to distinguish between real and generated videos.<n>Our method achieves high detection accuracy, above 90% on average, underscoring its effectiveness.
arXiv Detail & Related papers (2025-07-17T15:36:39Z) - AI-Generated Video Detection via Perceptual Straightening [10.189379841180285]
We propose ReStraV, a novel approach to distinguish natural from AI-generated videos.<n>Inspired by the "perceptual straightening" hypothesis, we quantify the temporal curvature and stepwise distance in the model's representation domain.<n>Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos.
arXiv Detail & Related papers (2025-07-01T09:04:21Z) - Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation [31.737159092430108]
We study different generative architectures, searching and identifying discriminative features that are unbiased, robust to impairments, and shared across models.<n>We introduce a novel data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues.<n>Our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models.
arXiv Detail & Related papers (2025-06-20T07:36:59Z) - DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning [58.70446237944036]
DAVID-X is the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales.<n>We present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning.<n>Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.
arXiv Detail & Related papers (2025-06-13T13:39:53Z) - BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation [77.55074597806035]
GenBuster-200K is a large-scale, high-quality AI-generated video dataset featuring 200K high-resolution video clips.<n>BusterX is a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning.
arXiv Detail & Related papers (2025-05-19T02:06:43Z) - ASF-Net: Robust Video Deraining via Temporal Alignment and Online
Adaptive Learning [47.10392889695035]
We propose a new computational paradigm, Alignment-Shift-Fusion Network (ASF-Net), which incorporates a temporal shift module.
We construct a LArge-scale RAiny video dataset (LARA) which supports the development of this community.
Our proposed approach exhibits superior performance in three benchmarks and compelling visual quality in real-world scenarios.
arXiv Detail & Related papers (2023-09-02T14:50:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.