English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce MABe22, a large-scale, multi-agent video and trajectorybenchmark to assess the quality of learned behavior representations. Thisdataset is collected from a variety of biology experiments, and includestriplets of interacting mice (4.7 million frames video+pose tracking data, 10million frames pose only), symbiotic beetle-ant interactions (10 million framesvideo data), and groups of interacting flies (4.4 million frames of posetracking data). Accompanying these data, we introduce a panel of real-lifedownstream analysis tasks to assess the quality of learned representations byevaluating how well they preserve information about the experimental conditions(e.g. strain, time of day, optogenetic stimulation) and animal behavior. Wetest multiple state-of-the-art self-supervised video and trajectoryrepresentation learning methods to demonstrate the use of our benchmark,revealing that methods developed using human action datasets do not fullytranslate to animal datasets. We hope that our benchmark and dataset encouragea broader exploration of behavior representation learning methods acrossspecies and settings.

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior