Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes

TL;DR

This paper introduces a comprehensive video dataset of mice solving complex lockboxes, facilitating the development of automated behavior recognition methods in computational neuroscience.

Contribution

It provides a novel, large-scale dataset with multi-view recordings and human annotations for fine-grained behavior analysis of mice in puzzle-solving tasks.

Findings

Pose-based action classification highlights challenges in automated labeling.

Dataset covers over 110 hours of behavior from mice solving lockboxes.

Benchmark results demonstrate current methods' limitations in fine-grained behavior recognition.

Abstract

Machine learning and computer vision methods have a major impact on the study of natural animal behavior, as they enable the (semi-)automatic analysis of vast amounts of video data. Mice are the standard mammalian model system in most research fields, but the datasets available today to refine such methods focus either on simple or social behaviors. In this work, we present a video dataset of individual mice solving complex mechanical puzzles, so-called lockboxes. The more than 110 hours of total playtime show their behavior recorded from three different perspectives. As a benchmark for frame-level action classification methods, we provide human-annotated labels for all videos of two different mice, that equal 13% of our dataset. Our keypoint (pose) tracking-based action classification framework illustrates the challenges of automated labeling of fine-grained behaviors, such as the manipulation of objects. We hope that our work will help accelerate the advancement of automated action and behavior classification in the computational neuroscience community. Our dataset is publicly available at https://doi.org/10.14279/depositonce-23850