[HTML][HTML] Open-source tools for behavioral video analysis: Setup, methods, and best practices

K Luxem, JJ Sun, SP Bradley, K Krishnan, E Yttri… - Elife, 2023 - elifesciences.org
Recently developed methods for video analysis, especially models for pose estimation and
behavior classification, are transforming behavioral quantification to be more precise …

[HTML][HTML] Keypoint-MoSeq: parsing behavior by linking point tracking to pose dynamics

C Weinreb, JE Pearl, S Lin, MAM Osman, L Zhang… - Nature …, 2024 - nature.com
Keypoint tracking algorithms can flexibly quantify animal movement from videos obtained in
a wide variety of settings. However, it remains unclear how to parse continuous keypoint …

[HTML][HTML] Identifying behavioral structure from deep variational embeddings of animal motion

K Luxem, P Mocellin, F Fuhrmann, J Kürsch… - Communications …, 2022 - nature.com
Quantification and detection of the hierarchical organization of behavior is a major challenge
in neuroscience. Recent advances in markerless pose estimation enable the visualization of …

Lightning Pose: improved animal pose estimation via semi-supervised learning, Bayesian ensembling and cloud-native open-source tools

D Biderman, MR Whiteway, C Hurwitz, N Greenspan… - Nature …, 2024 - nature.com
Contemporary pose estimation methods enable precise measurements of behavior via
supervised deep learning with hand-labeled video frames. Although effective in many cases …

3d implicit transporter for temporally consistent keypoint discovery

C Zhong, Y Zheng, Y Zheng, H Zhao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Keypoint-based representation has proven advantageous in various visual and robotic
tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on …

Unsupervised keypoints from pretrained diffusion models

E Hedlin, G Sharma, S Mahajan, X He… - Proceedings of the …, 2024 - openaccess.thecvf.com
Unsupervised learning of keypoints and landmarks has seen significant progress with the
help of modern neural network architectures but performance is yet to match the supervised …

3d human keypoints estimation from point clouds in the wild without human labels

Z Weng, AS Gorban, J Ji, M Najibi… - Proceedings of the …, 2023 - openaccess.thecvf.com
Training a 3D human keypoint detector from point clouds in a supervised manner requires
large volumes of high quality labels. While it is relatively easy to capture large amounts of …

BKinD-3D: self-supervised 3D keypoint discovery from multi-view videos

JJ Sun, L Karashchuk, A Dravid… - Proceedings of the …, 2023 - openaccess.thecvf.com
Quantifying motion in 3D is important for studying the behavior of humans and other
animals, but manual pose annotations are expensive and time-consuming to obtain. Self …

Autolink: Self-supervised learning of human skeletons and object outlines by linking keypoints

X He, B Wandt, H Rhodin - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Structured representations such as keypoints are widely used in pose transfer, conditional
image generation, animation, and 3D reconstruction. However, their supervised learning …

Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

M Azabou, M Mendelson, N Ahad… - Advances in …, 2024 - proceedings.neurips.cc
Unconstrained and natural behavior consists of dynamics that are complex and
unpredictable, especially when trying to predict what will happen multiple steps into the …