ICASSP'22 Training Strategies for Improved Lip-Reading; ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks
active 2023-08-22 → 2026-01-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 873 days from 2023-08-22 to 2026-01-10. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 10 total, peak 2 in a day. Comments: 7 total, peak 2 in a day. Stars: 141 total, peak 3 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 |
|---|---|---|---|---|
| SHAIIM04 | 3 | 0 | 0 | 1 |
| kyrie0520 | 3 | 0 | 0 | 2 |
| Rathi4research | 3 | 0 | 0 | 1 |
| mpc001 | 2 | 0 | 0 | 1 |
| BaochaoZhu | 2 | 0 | 0 | 1 |
| seuklee1025 | 1 | 0 | 0 | 0 |
| StephanPan | 1 | 0 | 0 | 1 |
| souvikg544 | 1 | 0 | 0 | 0 |
| rzwang111 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#65kyrie05202024-11-01 03:25The code for the Knowledge Distillation loss
- Issue comment#65kyrie05202024-11-01 03:23The code for the Knowledge Distillation loss
- Issue#66kyrie05202024-10-31 15:36预处理问题
- Issue#65BaochaoZhu2024-10-31 07:48The code for the Knowledge Distillation loss
- Issue comment#24BaochaoZhu2024-10-31 07:45The code for the Knowledge Distillation loss
- Issue comment#14StephanPan2024-01-05 02:20Reproduce on LRW1000,only get 38.6,how can get 41.4?
- Issue#64souvikg5442023-11-07 18:52How are you dealing with varied length of input - like some are 29,28,27.
- Issue#63Rathi4research2023-10-29 17:02How to create .pkl file for my own video
- Issue#62rzwang1112023-10-16 06:41Your work is excellent! How can I calculate lip reading loss L between the face my model reders and my ground truth image?
- Issue#61SHAIIM042023-10-05 00:17KeyError: 'optimizer_state_dict' arise with Pretrined model
- Issue#58SHAIIM042023-10-05 00:09RuntimeError: CUDA error: device-side assert triggered
- Issue comment#58SHAIIM042023-10-05 00:09RuntimeError: CUDA error: device-side assert triggered
- Issue#60mpc0012023-10-03 15:00Not able to evaluate visual-only performance using the pre-processed npz files
- Issue comment#60Rathi4research2023-09-25 15:32Not able to evaluate visual-only performance using the pre-processed npz files
- Issue comment#60mpc0012023-09-17 14:51Not able to evaluate visual-only performance using the pre-processed npz files
- Issue#60Rathi4research2023-09-16 14:19Not able to evaluate visual-only performance using the pre-processed npz files
- Issue#59seuklee10252023-08-29 07:04Can you tell me how to get word boundary from real reasoning?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 141 stars here means stars gained during the window, not the repo's star count.