deepfake/README.md

Deepfake

author: Zhuoran Yu

Description

Deepfake techniques, which present realistic AI-generated videos of people doing and saying fictional things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.

This operator predicts the probability of a fake video for a given video.This is an adaptation from DeepfakeDetection.

Code Example

Load videos from path '/home/test_video' and use deepfake operator to predict the probabilities of fake videos.

from towhee.dc2 import pipe, ops, DataCollection

p = (
    pipe.input('path')
        .map('path', 'scores', ops.towhee.deepfake)
        .output('scores')
)

DataCollection(p('./deepfake_video/test/aagfhgtpmv.mp4').get_dict()).show()

[0.99]

Interface

A deepfake operator takes videos' paths as input. It predicts the probabilities of fake videos.The higher the score, the higher the probability of it being a fake video.(It can be considered to be a fake video with score higher than 0.5)

Parameters:

filepath: str

Absolute address of the test videos.

Returns: list

The probabilities of videos being fake ones.

# More Resources

- [Vector Search and RAG - Balancing Accuracy and Context - Zilliz blog](https://zilliz.com/blog/vector-search-and-rag-balancing-accuracy-and-context): In this article, we cover AI Hallucinations and how RAG can help solve the issue. Christy demonstrated a great explanation of how building RAG requires careful choices of embedding models, indexes, and semantic search approaches.

• How to Get the Right Vector Embeddings - Zilliz blog: A comprehensive introduction to vector embeddings and how to generate them with popular open-source models.
• What is a Convolutional Neural Network? An Engineer's Guide: Convolutional Neural Network is a type of deep neural network that processes images, speeches, and videos. Let's find out more about CNN.
• The guide to clip-vit-base-patch32 | OpenAI: clip-vit-base-patch32: a CLIP multimodal model variant by OpenAI for image and text embedding.
• Building a Video Analysis System with Milvus Vector Database - Zilliz blog: Learn how Milvus powers the AI analysis of video content.
• Building an Intelligent QA System with NLP and Milvus - Zilliz blog: The Next-Gen QA Bot is here
• Evaluating Your Embedding Model - Zilliz blog: Review some practical examples to evaluate different text embedding models.
• What is a Generative Adversarial Network? An Easy Guide: Just like we classify animal fossils into domains, kingdoms, and phyla, we classify AI networks, too. At the highest level, we classify AI networks as "discriminative" and "generative." A generative neural network is an AI that creates something new. This differs from a discriminative network, which classifies something that already exists into particular buckets. Kind of like we're doing right now, by bucketing generative adversarial networks (GANs) into appropriate classifications. So, if you were in a situation where you wanted to use textual tags to create a new visual image, like with Midjourney, you'd use a generative network. However, if you had a giant pile of data that you needed to classify and tag, you'd use a discriminative model.
• Real-Time GenAI without Hallucination Using Confluent & Zilliz Cloud: nan