Animal Pose Estimation

22 papers with code • 6 benchmarks • 16 datasets

Animal pose estimation is the task of identifying the pose of an animal.

( Image credit: Using DeepLabCut for 3D markerless pose estimation across species and behaviors )


Use these libraries to find Animal Pose Estimation models and implementations

Most implemented papers

AP-10K: A Benchmark for Animal Pose Estimation in the Wild

AlexTheBad/AP-10K 28 Aug 2021

The experimental results provide sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.

APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking

pandorgan/apt 12 Jun 2022

Based on APT-36K, we benchmark several representative models on the following three tracks: (1) supervised animal pose estimation on a single frame under intra- and inter-domain transfer learning settings, (2) inter-species domain generalization test for unseen animals, and (3) animal pose estimation with animal tracking.

SuperAnimal pretrained pose estimation models for behavioral analysis

DeepLabCut/DeepLabCut 14 Mar 2022

Quantification of behavior is critical in applications ranging from neuroscience, veterinary medicine and animal conservation efforts.

Multi-animal pose estimation, identification and tracking with DeepLabCut

deeplabcut/madlc_naturemethods2022 Nature Methods 2022

Estimating the pose of multiple animals is a challenging computer vision problem: frequent interactions cause occlusions and complicate the association of detected keypoints to the correct individuals, as well as having highly similar looking animals that interact more closely than in typical multi-human scenarios.

11K Hands: Gender recognition and biometric identification using a large dataset of hand images

mahmoudnafifi/11K-Hands 12 Nov 2017

In this work, we propose a large dataset of human hand images (dorsal and palmar sides) with detailed ground-truth information for gender recognition and biometric identification.

Markerless tracking of user-defined features with deep learning

DeepLabCut/DeepLabCut 9 Apr 2018

Quantifying behavior is crucial for many applications in neuroscience.

Pretraining boosts out-of-domain robustness for pose estimation

DeepLabCut/DeepLabCut 24 Sep 2019

Neural networks are highly effective tools for pose estimation.

WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans

iteal/wormpose Plos Computational Biology 2021

An important model system for understanding genes, neurons and behavior, the nematode worm C. elegans naturally moves through a variety of complex postures, for which estimation from video data is challenging.

Structured Context Enhancement Network for Mouse Pose Estimation

FeixiangZhou/GM-SCENet 1 Dec 2020

However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours.