tapnet
co-tracker
| tapnet | co-tracker | |
|---|---|---|
| 3 | 6 | |
| 1,058 | 2,444 | |
| 3.7% | 4.5% | |
| 8.2 | 6.9 | |
| 17 days ago | about 22 hours ago | |
| Python | Jupyter Notebook | |
| Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tapnet
-
Meta AI releases CoTracker, a model for tracking any points (pixels) on a video
Neat. It's mentioned on Facebook's page, but here Google's version of point tracking: https://deepmind-tapir.github.io
-
Meet TAP-Vid: A Dataset of Videos Along With Point Tracks, Either Manually Annotated or Obtained From A Simulator
Quick Read: https://www.marktechpost.com/2022/11/26/meet-tap-vid-a-dataset-of-videos-along-with-point-tracks-either-manually-annotated-or-obtained-from-a-simulator/ Paper: https://arxiv.org/pdf/2211.03726.pdf Github link: https://github.com/deepmind/tapnet
- Tap-Vid: A Benchmark for Tracking Any Point in a Video
co-tracker
- What things are happening in ML that we can't hear oer the din of LLMs?
-
ML Engineering Online Book
Yes, I think this is very tractable for a first project. I've played around with using AI to do optical-only with pose detection models -- if I had to do it again, I would probably start with this model and try to get it running locally:
https://github.com/facebookresearch/co-tracker
This sounds like a perfect place for you to get started!
- FLaNK Stack Weekly 5 September 2023
-
CoTracker: A Revolutionary 2D Point Video Tracker
(arXiv) (GitHub)
-
Meta AI releases CoTracker, a model for tracking any points (pixels) on a video
LICENSE
Attribution-NonCommercial 4.0 International
https://github.com/facebookresearch/co-tracker/blob/main/LIC...
What are some alternatives?
omnimotion
paxml - Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
ModelNet40-C - Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296
FLaNK-HuggingFace-BLOOM-LLM - https://huggingface.co/bigscience/bloom into NiFi
Ghost-DeblurGAN - This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size and a rapid inference time. The motivation is to boost marker detection in robotic applications, however, you may use it for other applications definitely.
puck - The visual editor for React
LFattNet - Attention-based View Selection Networks for Light-field Disparity Estimation
openaidemo - Demo of how access the OpenAI API using Java 17
opendr - A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning
morphir - A universal language for business and technology
fashion-mnist - A MNIST-like fashion product database. Benchmark :point_down: