Built independently by an author, for readers. Read the story and support ChapterPal

keyword

fake video detection task

The fake video detection task is a computer vision and machine learning objective focused on automatically determining whether a video consists of authentic real-world footage or synthetically generated and manipulated content. Driven by the advancement of generative artificial intelligence technologies, including deepfake tools and text-to-video diffusion models, this task requires algorithms to evaluate visual media for signs of artificial synthesis. Detection approaches typically analyze spatial anomalies within individual frames, temporal inconsistencies across consecutive frames, compression traces, and statistical artifacts characteristic of generative model architectures. The primary goals of this task include preventing the spread of visual misinformation, verifying media integrity for digital forensics, and supporting automated content moderation across digital platforms.

1 item

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Wenhao Wang, Yi Yang

OrganizationsUniversity of Technology SydneyZhejiang University

Why you should read this

Introduces VidProM, the first large-scale prompt-gallery dataset containing 1.67 million real-user text-to-video prompts paired with 6.69 million synthesized videos from four diffusion models to advance research in video prompt engineering, efficient generation, and synthetic video detection.

The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 Million unique text-to-Video Prompts from real users. Additionally, this dataset includes 6.69 million videos generated by four state-of-the-art diffusion models, alongside some related data. We initially discuss the curation of this large-scale dataset, a process that is both time-consuming and costly. Subsequently, we underscore the need for a new prompt dataset specifically designed for text-to-video generation by illustrating how VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Our extensive and diverse dataset also opens up many exciting new research areas. For instance, we suggest

Added

2026-09-26