Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Animal Pose Estimation

3260 papers • 126 benchmarks • 313 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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in animal-pose-estimation-7

Trend

Dataset

Best Model

Actions

AP-10K

AP-10K

Horse-10

Horse-10

TriMouse-161

TriMouse-161

Libraries

i

Use these libraries to find animal-pose-estimation-7 models and implementations

DeepLabCut/DeepLabCut

5 papers 4,652

Datasets

AP-10K

Animal Kingdom

Animal-Pose Dataset

Animal-Pose Dataset

StanfordExtra

ATRW

Animal3D

Subtasks

No subtasks available.

Most implemented papers

SuperAnimal pretrained pose estimation models for behavioral analysis

Alexander Mathis, Mackenzie W. Mathis, Maxime Vidal, Steffen Schneider, Jessy Lauer, Shaokai Ye, Anastasiia Filippova, Tian Qiu•Sun Mar 13 2022

This work presents SuperAnimal, a method to develop unified foundation models that can be used on over 45 species, without additional manual labels, that show excellent performance across six pose estimation benchmarks.

72

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Marmoset-8K

Marmoset-8K

Fish-100

Fish-100

StanfordExtra

StanfordExtra

Animal-Pose Dataset

Animal-Pose Dataset

Animal3D

Animal3D

Horse-10

Horse-10

AwA Pose

TriMouse-161

MBW - Zoo Dataset

MBW - Zoo Dataset

0

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

D. Tao, Yufei Xu, Jing Zhang, Wei Zhao, Hang Yu, Ziyu Guan•Fri Aug 27 2021

This paper proposes AP-10K, the first large-scale benchmark for mammal animal pose estimation, and provides sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.

160 0

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

Junjie Yang, Yufei Xu, Jing Zhang, Dacheng Tao, Long Lan, Yuxiang Yang•Sat Jun 11 2022

This work proposes APT-36K, the first large-scale benchmark for animal pose estimation and tracking, and benchmark several representative models on the following three tracks: (1) supervisedAnimal pose estimation on a single frame under intra- and inter-domain transfer learning settings, (2) inter-species domain generalization test for unseen animals, and

70 0

Multi-animal pose estimation, identification and tracking with DeepLabCut

Alexander Mathis, Mackenzie W. Mathis, Steffen Schneider, Jessy Lauer, Mu Zhou, Shaokai Ye, William Menegas, Tanmay Nath, Mohammed Mostafizur Rahman, V. Di Santo, Daniel Soberanes, G. Feng, Venkatesh N. Murthy, G. Lauder, Catherine Dulac•Thu Mar 31 2022

DeepLabCut is extended to enable multi-animal pose estimation, animal identification and tracking, thereby enabling the analysis of social behaviors and illustrating the power of this framework with four datasets varying in complexity.

419 0

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

M. Afifi•Sat Nov 11 2017

A two-stream convolutional neural network which accepts hand images as input and predicts gender information from these hand images is designed, and the dorsal side of human hands is found to have effective distinctive features similar to, if not better than, those available in the palmar side ofhuman hand images.

187 0

X-Pose: Detecting Any Keypoints

Ailing Zeng, Ruimao Zhang, Jie Yang, Lei Zhang•Wed Oct 11 2023

X-Pose is proposed, a novel end-to-end framework with multi-modal prompts to detect multi-object keypoints for any articulated, rigid, and soft objects within a given image, which demonstrates X-Pose's strong fine-grained keypoint localization and generalization abilities across image styles, object categories, and poses.

14 0

Pretraining boosts out-of-domain robustness for pose estimation

Alexander Mathis, Mackenzie W. Mathis, M. Bethge, Mert Yuksekgonul, Steffen Schneider, Mert Yüksekgönül•Mon Sep 23 2019

This work probes the generalization ability with three architecture classes (MobileNetV2s, ResNets, and EfficientNets) for pose estimation and shows that better ImageNet models generalize better across animal species, and demonstrates that transfer learning is beneficial for out-of-domain robustness.

136 0

ImageNet performance correlates with pose estimation robustness and generalization on out-of-domain data

Alexander Mathis, Mackenzie W. Mathis, M. Bethge, Mert Yuksekgonul, Thomas Biasi, Byron Rogers•Tue Dec 31 2019

This work develops a novel dataset of 30 horses that allowed for both “within-domain” and “out-of-domain” (unseen horse) benchmarking - this is a crucial test for robustness that current human pose estimation benchmarks do not directly address.

8 0

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

Laetitia Hebert, Tosif Ahamed, Antonio C. Costa, Liam O’Shaugnessy, G. Stephens•Thu Jul 09 2020

An open-source Python package, WormPose, is introduced for 2D pose estimation in C. elegans, including self-occluded, coiled shapes, and is effective and adaptable for imaging conditions across worm tracking efforts.

49 0

Adding a benchmark result helps the community track progress.

Animal Pose Estimation | State-of-the-Art