https://xitter.gq/t.co/KexlLscBxP
Ann Arbor, MI
Joined June 2020
- Tweets7
- Following56
- Followers22
- Likes9
Gaurav Kaul retweeted
We present Global Matching Random Walks, a simple self-supervised approach to the Tracking Any Point (TAP) problem, accepted to #ECCV2024. We train a global matching transformer to find cycle consistent tracks through video via contrastive random walks (CRW).
Detect Any Mouse Model accepted into Scientific Reports!
Paper: nature.com/articles/s41598-0…
Project page: web.eecs.umich.edu/gkaul/DAM…
GitHub: github.com/backprop64/DAMM
Datasets: huggingface.co/datasets/gaur…
W/ Jonathan McDevitt, Justin Johnson (@jcjohnss), Ada Eban-Rothschild
(🧵 below 1/6)
(5/6) All in all, Detect Any Mouse Model, or DAMM for short, is great at detecting mice out of the box and can quickly adapt to new settings with just a few training points!
Check out how you can use DAMM in your projects via our GitHub, and explore our datasets on Hugging Face.
1
124
(6/6)Huge thanks to @UM_MICDE for supporting this work with the catalyst grant, @OpenBehavior for creating an open source animal behavior video repository ~ along with all the scientist who uploaded their videos, and @huggingface for hosting our datasets!