VPN: Video Provenance Network for Robust Content Attribution
We present VPN - a content attribution method for recovering provenance information from videos shared online. Platforms, and users, often transform video into different quality, codecs, sizes, shapes, etc. or slightly edit its content such as adding text or emoji, as they are redistributed online. We learn a robust search embedding for matching such video, invariant to these transformations, using full-length or truncated video queries. Once matched against a trusted database of video clips, associated information on the provenance of the clip is presented to the user. We use an inverted index to match temporal chunks of video using late-fusion to combine both visual and audio features. In both cases, features are extracted via a deep neural network trained using contrastive learning on a dataset of original and augmented video clips. We demonstrate high accuracy recall over a corpus of 100,000 videos.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EKILA: Synthetic Media Provenance and Attribution for Generative Art
We present EKILA; a decentralized framework that enables creatives to receive recognition and reward for their contributions to generative AI (GenAI). EKILA proposes a robust visual attribution technique and combines thi…
When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing
When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environme…
SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling
Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing exter…
Image RetrievalBeyond Pixels: Image Provenance Analysis Leveraging Metadata
Creative works, whether paintings or memes, follow unique journeys that result in their final form. Understanding these journeys, a process known as "provenance analysis", provides rich insights into the use, motivation,…
graph constructionImage ForensicsImplicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial inves…