New paper out in the lab on collective gaze following in pigeons in iScience!

Coolest experimental design ever🤭

Shout out Janet for my favorite figure so far

Back to see what the world of computer vision has to offer 😌

Using the framework to extract coded behavioural metrics (e.g feeding rate, visit rates), we also show that the rates extracted are highly correlated

Using the widely used object detector YOLO, we show that if you prepare your dataset in a slightly creative way (e.g drawing a box around a Siberian Jay's beak touching food), the model can be used to detect behviours from videos effectively

Second paper out this week 😱😱

We present YOLO-Behaviour, a flexible, easy to implement, robust framework for automated behavioural annotation from videos, published in @methodsinecoevol.bsky.social!!

[paper] doi.org/10.1111/2041...
[documentation] alexhang212.github.io/YOLO_Behavio...

We found that network metrics are largely robust to different association definitions, yielding repeatable and consistent results across methods. However, we observed subtle differences influenced by feeder type and species ecology.

In this paper, we compared three approaches: (1) strict time-window, (2) co-occurrence, and (3) arrival time methods to define associations for house sparrows on Lundy Island, UK, and Broken Hill, Australia; great tits in Wytham Woods, UK; and sociable weavers in Benfontein National Park.

Made my way back on Lundy after 3 years! 🌄

Time to stare at some sparrows
@jj255.bsky.social