[NeurIPS 2024] This is the official repo of the paper "Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-syncing DeepFakes".
active 2024-01-09 → 2026-03-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 797 days from 2024-01-09 to 2026-03-15. Pushes: 20 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 28 total, peak 5 in a day. Comments: 29 total, peak 5 in a day. Stars: 124 total, peak 7 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| AaronComo | 32 | 20 | 0 | 4 |
| amit154154 | 5 | 0 | 0 | 4 |
| twilight2001 | 4 | 0 | 0 | 4 |
| Mohand995 | 4 | 0 | 0 | 3 |
| JiaLiangShen | 4 | 0 | 0 | 4 |
| FastWind123 | 3 | 0 | 0 | 3 |
| diksham-flwls | 2 | 0 | 0 | 0 |
| MatMB115 | 2 | 0 | 0 | 1 |
| AMEERAZAM08 | 2 | 0 | 0 | 1 |
| mamarasulovs | 1 | 0 | 0 | 0 |
| ZXX-Coding | 1 | 0 | 0 | 1 |
| mribrahim | 1 | 0 | 0 | 1 |
| hefeng-0411 | 1 | 0 | 0 | 1 |
| dav-joy-thon | 1 | 0 | 0 | 0 |
| OliverGrein | 1 | 0 | 0 | 0 |
| Queequeg92 | 1 | 0 | 0 | 0 |
| robotsouper | 1 | 0 | 0 | 0 |
| lalall1 | 1 | 0 | 0 | 0 |
| conkeur | 1 | 0 | 0 | 1 |
| nzrjamm | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#21guyrose32025-12-03 11:16Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#21mribrahim2025-11-27 21:21Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#21FastWind1232025-07-09 09:33Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#21FastWind1232025-07-09 02:25Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#11FastWind1232025-07-07 09:53what head/face detector did you use?
- Issue comment#21amit1541542025-05-22 13:47Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#21Mohand9952025-05-22 13:23Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#21amit1541542025-05-22 13:04Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#22Mohand9952025-05-22 12:49single video inference script
- Issue comment#21Mohand9952025-05-22 12:35Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#22amit1541542025-05-21 13:55single video inference script
- Issue#22Mohand9952025-05-21 09:48single video inference script
- Issue comment#16amit1541542025-05-20 22:41Testing with one video
- Issue#21amit1541542025-05-20 22:18Poor Accuracy When Evaluating the Model on My Own Dataset
- Issue comment#17JiaLiangShen2025-05-08 08:54Why Frame Crop only use the first frame?
- Issue comment#17JiaLiangShen2025-05-08 08:20Why Frame Crop only use the first frame?
- Issue comment#17JiaLiangShen2025-05-08 08:18Why Frame Crop only use the first frame?
- Issue comment#17JiaLiangShen2025-05-08 08:17Why Frame Crop only use the first frame?
- Issue comment#9ZXX-Coding2025-04-20 15:58Training code
- Issue#20KeithKKRR2025-04-19 19:02Dataset Downloading Issue
- Issue#19dav-joy-thon2025-04-17 08:35issues about training dataset
- Issue#18robotsouper2025-04-11 19:44RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
- Issue#15razisamuely2025-02-06 11:18Accuracy on validaton set is less (0.93) than your report (0.95)
- Issue#14OliverGrein2025-01-29 20:11Train-Test Split
- Issue comment#12twilight20012025-01-09 13:10wav files
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.