Skip to content

The official implementation for LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection

Python · active 2023-11-152026-05-28 (UTC)

Complete coverage26,579 / 26,579 hourly files (100%) · 2 absent upstream2023-08-152026-08-26 (UTC)
Events
261
Pushes
24
Pull requests
1
Issues
36
Stars
147
Forks
20

Activity over time

Daily event counts in the loaded window

Line chart, 926 days from 2023-11-15 to 2026-05-28. Pushes: 24 total, peak 11 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 36 total, peak 3 in a day. Comments: 25 total, peak 3 in a day. Stars: 147 total, peak 9 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Pull request#27vishnuexe2025-08-11 08:36
  • Issue#26Cheng159939179132025-04-28 03:50
    检测结果为什么都是负值呢
  • Issue comment#18bimo-adiparwa2025-04-28 01:30
    Why the results is always < 0 on deepfake or real image
  • Issue comment#18Cheng159939179132025-04-26 12:34
    Why the results is always < 0 on deepfake or real image
  • Issue comment#4wuwuwuyue2025-04-15 06:50
    Train on FF++ C23
  • Issue comment#4wuwuwuyue2025-04-15 06:42
    Train on FF++ C23
  • Issue#4wuwuwuyue2025-04-15 06:42
    Train on FF++ C23
  • Issue comment#4userwxp2025-04-13 03:36
    Train on FF++ C23
  • Issue comment#18Cheng159939179132025-04-09 06:50
    Why the results is always < 0 on deepfake or real image
  • Issue comment#21AryaPulkit2025-03-30 16:12
    Box() takes no arguments
  • Issue#24zuiluorenjian2025-03-19 11:05
    video extraction frame
  • Issue#24zuiluorenjian2025-03-14 03:41
    video extraction frame
  • Issue comment#23Swilder72025-02-20 05:49
    Why is the generalization performance of the model I trained poor?
  • Issue#23Swilder72025-02-20 05:47
    Why is the generalization performance of the model I trained poor?
  • Issue#20shui-tian-ju-shi2024-12-28 04:50
    weights of EfficientNet + EFPN pre-trained on ImageNet
  • Issue#21changgzz2024-12-27 04:26
    Box() takes no arguments
  • Issue comment#18lu-xinyuan2024-12-10 03:03
    Why the results is always < 0 on deepfake or real image
  • Issue#20shui-tian-ju-shi2024-12-02 04:55
    weights of EfficientNet + EFPN pre-trained on ImageNet
  • Issue comment#11Swilder72024-11-26 10:22
    dataset initialization error
  • Issue comment#19Bytebender32024-11-26 03:42
    Annotation file for FF++ used for Training
  • Issue comment#7recluzegeek2024-11-24 02:10
    Empty preprocessed result.
  • Issue comment#16recluzegeek2024-11-24 02:04
    while executingimage_crop.py
  • Issue#19recluzegeek2024-11-23 10:45
    Annotation file for FF++ used for Training
  • Issue comment#18oracleaivision2024-11-07 22:11
    Why the results is always < 0 on deepfake or real image
  • Issue#18bimo-adiparwa2024-10-31 03:26
    Why the results is always < 0?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 147 stars here means stars gained during the window, not the repo's star count.