Table 1 Multi-animal pose estimation dataset characteristics

From: Multi-animal pose estimation, identification and tracking with DeepLabCut

Feature

Mouse

Pups

Marmosets

Fish

Labeled frames

161

542

7,600

100

Keypoints

12

5 (+12)

15

5

Individuals

3

2 (+1)

2

14

GT identity

No

No

Yes

No

Annotated video frames

11,645

2,670

15,000

1,100

Total duration (s)

385

180

600

36

  1. Number of labeled training frames, keypoints and individuals. Keypoint number in brackets relate to the unique animal in the frame, and unique individual in brackets is noted, that is, one parenting mouse. Animal identity was only annotated for the marmosets. For tracking, separate videos are used and the total number of densely human-annotated video frames (and their combined duration in seconds) is also indicated.
Back to article page