#SfN2025 @deeplabcut.bsky.social 3 poster on Monday morning. Overall, DeepLabCut 3.0 provides an integrative suite of tools for project management, deep learning for animal pose, and integration with many tools such as #Cebra, DLC2action, kpt-Moseq, etc.
www.abstractsonline.com/pp8/#!/21171...

Winter is coming.

Count me in too!

Absolutely, please note this is a dataset and machine learning benchmark article. The behavior study is coming!

We’ll present the first benchmark at @neuripsconf.bsky.social — there is much more to come!

Amazing work from co-first authors Andy Bonnetto and Haozhe Qi and a big team! The smart kitchen was built in collaboration with Silvestro Micera, Friedhelm Hummel and @marcpollefeys.bsky.social.

Leveraging this multi-modal dataset, we propose four benchmarks to advance behavior understanding and modeling through 1) a vision-language benchmark, 2) a semantic text-to-motion generation benchmark, 3) a multi-modal action recognition benchmark, 4) a pose-based action segmentation benchmark.

Here, we introduce the EPFL-Smart-Kitchen-30 dataset, collected in a noninvasive motion capture platform inside a kitchen environment. Leveraging this multi-modal dataset, we propose four benchmarks to advance behavior understanding and modeling!