Shaif Chowdhury, Moshiur Rahman Tonmoy · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28524 · cited by 0 works (OpenAlex) · open-access PDF
Alguns dos avanços recentes levantaram preocupações sobre a reprodução de conteúdos visuais protegidos por direitos autorais. No entanto, a detecção de vazamentos de direitos autorais em vídeos gerados permanece em grande parte inexplorada. Neste artigo, apresentamos um novo conjunto de dados de referência para a detecção de vazamentos de direitos autorais, composto por 50 conceitos protegidos por direitos autorais, cada um com 5 imagens. Para cada conceito, temos 5 vídeos criados usando o modelo de geração de imagens com direitos autorais e o modelo de geração de vídeos com apenas prompt. Depois disso, desenvolvemos um conjunto de ferramentas de IA baseado em um quadro de recuperação de contraste que formula a detecção de vazamentos de direitos autorais como um problema de recuperação de vídeo de imagem para imagem, correspondendo a incorporações de vídeo agregadas contra um
Machine translation (Meta M2M100); the English original follows.
Video generation models can create realistic-looking video footage from images and text prompts. Some of the recent advances have raised concerns about the reproduction of copyrighted visual content. However, copyright leakage detection in generated videos remains largely unexplored. In this paper, we introduce a new benchmark data set for copyright leakage detection, comprising 50 copyrighted concepts, each with 5 images. For each concept, we have 5 videos created using the image+prompt video generation model and the prompt-only video generation model. Following that, we develop an AI toolset based on a contrastive retrieval framework that formulates copyright leakage detection as a video-to-image retrieval problem by matching aggregated video frame embeddings against a database of copyrighted image embeddings. Our method uses a single similarity threshold and retrieves the most similar copyrighted reference as supporting evidence. We conducted experiments showing strong retrieval and detection performance, achieving 99.6\% detection accuracy with only a single false negative. These results show the effectiveness of the retrieval-based method for scalable and explainable copyright leakage detection in AI-generated videos. Data can be accessed publicly from https://zenodo.org/records/21386117 and the source code for this project is publicly available at https://github.com/Shaif95/video-cp-Leakage.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Scalability, Leakage (economics), Artificial intelligence, Information retrieval, Benchmark (surveying)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28524, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange