This dataset was collected to quantify inter-annotator variability in manual labeling of social behaviors in freely interacting mice. We provided a group of graduate students, postdocs, and technicians in the Anderson lab with written descriptions of close investigation, mounting, and attack behaviors (included below), and instructed them to sc...

Multi-agent behavior modeling aims to understand the interactions that occur between agents. We present a multi-agent dataset from behavioral neuroscience, the Caltech Mouse Social Interactions (CalMS21) Dataset. Our dataset consists of trajectory data of social interactions, recorded from videos of freely behaving mice in a standard resident-in...

Our Fly-vs-Fly dataset contains 22 hours of video showing pairs of fruit flies engaging in 10 social interactions in three different contexts; it is fully annotated by experts,and published with articulated pose trajectory features. The dataset is organized into three sub-datasets: Boy meets boy, which is designed to study the sequence of action...

Real-world behavior is often shaped by complex interactions between multiple agents. To scalably study multi-agent behavior, advances in unsupervised and self-supervised learning have enabled many different behavioral representations to be learned from trajectory data. However, such representation learning approaches are generally evaluated on s...

The study of naturalistic social behavior requires quantification of animals' interactions. This is generally done through manual annotation—a highly time consuming and tedious process. Recent advances in computer vision enable tracking the pose (posture) of freely-behaving animals. However, automatically and accurately classifying complex socia...

Behavioral and chemical data for a benzoquinone producing bug. Provided DeepLabCut project with behavioral movies, hand labeled frames for network training, neural network, and outputs from DLC and other outputs from custom machine vision pipeline. Also contains endpoint assay chemical readouts from a solid phase micro-extraction deployed during...

This dataset contains trained neural network models for mouse detection and pose estimation, and trained classifiers for mouse behavior annotation. These model files accompany the MARS end-user software posted at https://github.com/neuroethology/MARS, for MARS version 1.8. To use these trained models, download the models.zip file and unzip into...

The study of naturalistic social behavior requires quantification of animals' interactions. This is generally done through manual annotation—a highly time consuming and tedious process. Recent advances in computer vision enable tracking the pose (posture) of freely-behaving animals. However, automatically and accurately classifying complex socia...

Video 1 of jumping sequences filmed at 20 kHz to measure velocity and other behavioural kinematics of S. carpocapsae.

Video 2 of jumping filmed at 20 kHz to measure velocity and other behavioural kinematics of S. carpocapsae.