SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.05630 · CVPR · 2021

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

Ziwei Liu, Siyu Chen, Jing Shao, Luchuan Song, Lu Sheng, Guojun Yin, Yinan He, Bei Gan, Yichun Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

DeeperForensics-1.0 DFDC ForgeryNet 10 ! 10 " 10 # 10 $ 10 % 10 & 10 ' 10 ( 10 ! 10 " Figure 1: ForgeryNet is a new mega-scale face forgery dataset with comprehensive annotations and four forgery analysis tasks. It contains thousands of subjects, various manipulation methods and diverse re-rendering processes. In (a), can you distinguish which images are forged?

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.05630")
get_code_for_paper("2103.05630")
have("2103.05630")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.05630.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.05630.svg)](https://syntology.ai/paper/2103.05630)

Connect an agent — have() is free.