SOTAVerified

Animal Pose Estimation

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 )

Papers

Showing 1–48 of 48 papers

TitleStatusHype
MBE-ARI: A Multimodal Dataset Mapping Bi-directional Engagement in Animal-Robot InteractionCode0
Probabilistic Prompt Distribution Learning for Animal Pose EstimationCode1
Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based trackingCode0
Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose EstimationCode1
MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection—0
Edge Weight Prediction For Category-Agnostic Pose EstimationCode1
Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth AnalysisCode1
Unsupervised Prior Learning: Discovering Categorical Pose Priors from Videos—0
Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data—0
PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions—0
CNN Based Flank Predictor for Quadruped Animal Species—0
CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationCode1
Domain adaptive pose estimation via multi-level alignmentCode0
Animal Avatars: Reconstructing Animatable 3D Animals from Casual VideosCode2
APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and BeyondCode1
A Graph-Based Approach for Category-Agnostic Pose EstimationCode2
Telling Left from Right: Identifying Geometry-Aware Semantic CorrespondenceCode1
X-Pose: Detecting Any KeypointsCode2
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape—0
Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior—0
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguityCode1
SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose EstimationCode0
ScarceNet: Animal Pose Estimation with Scarce AnnotationsCode1
3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion captureCode1
ViTPose++: Vision Transformer for Generic Body Pose EstimationCode3
Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real DataCode0
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal PoseCode1
APT-36K: A Large-scale Benchmark for Animal Pose Estimation and TrackingCode1
Animal Kingdom: A Large and Diverse Dataset for Animal Behavior UnderstandingCode1
SemiMultiPose: A Semi-supervised Multi-animal Pose Estimation Framework—0
Multi-animal pose estimation, identification and tracking with DeepLabCutCode1
A Unified Framework for Domain Adaptive Pose EstimationCode1
SuperAnimal pretrained pose estimation models for behavioral analysisCode5
Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning—0
Incremental Learning for Animal Pose Estimation using RBF k-DPP—0
AP-10K: A Benchmark for Animal Pose Estimation in the WildCode1
SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation—0
T-LEAP: Occlusion-robust pose estimation of walking cows using temporal informationCode1
From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose EstimationCode1
AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the WildCode1
Structured Context Enhancement Network for Mouse Pose EstimationCode0
Continuous Surface EmbeddingsCode1
ImageNet performance correlates with pose estimation robustness and generalization on out-of-domain data—0
WormPose: Image synthesis and convolutional networks for pose estimation in C. elegansCode1
Pretraining boosts out-of-domain robustness for pose estimation—0
Cross-Domain Adaptation for Animal Pose Estimation—0
Markerless tracking of user-defined features with deep learning—0
11K Hands: Gender recognition and biometric identification using a large dataset of hand imagesCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTPose+-HAP82.4—Unverified
2ViTPose+-LAP80.4—Unverified
3SuperAnimal-HRNetw32AP80.11—Unverified
4UniPoseAP79.2—Unverified
5ViTPose+-BAP74.5—Unverified
6HRNet-w48AP73.1—Unverified
7HRNet-w32AP72.2—Unverified
8ViTPose+-S ViT-SAP71.4—Unverified
9SimpleBaseline-ResNet50AP68.1—Unverified
10zero-shot SuperAnimal-HRNetw32AP68.04—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepLabCut-EfficientNet-B6[email protected] (OOD)88.4—Unverified
2DeepLabCut-EfficientNet-B4[email protected] (OOD)86.9—Unverified
3DeepLabCut-RESNET-101[email protected] (OOD)84.3—Unverified
4DeepLabCut-RESNET 50[email protected] (OOD)81.3—Unverified
5DeepLabCut-MOBILENETV2-1[email protected] (OOD)77.6—Unverified
6DeepLabCut-MOBILENETV2 0.35[email protected] (OOD)63.5—Unverified
7mmpose HRNet-w32 (w/ImageNet pretrained weights)Normalized Error (OOD)0.18—Unverified
8SuperAnimal-Quadruped HRNet-w32Normalized Error (OOD)0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1BUCTD-CoAM-W48 (DLCRNet)mAP99.1—Unverified
2SuperAnimal HRNetw32mAP98.55—Unverified
3DLCRNetmAP95.8—Unverified
4ResNet50_s4graph11mAP93—Unverified
5DLCRNet_ms4graph11mAP92—Unverified
6CID-W32mAP86.8—Unverified
7zero-shot SuperAnimal HRNetw32mAP76.14—Unverified
#ModelMetricClaimedVerifiedStatus
1HRNet-W48 + Faster R-CNNmAP89.1—Unverified
2BUCTD-preNet-W48 (DLCRNet)mAP88.7—Unverified
3BUCTD-preNet-W48 (CID-W32)mAP88—Unverified
4DLCRNet_ms4graph9mAP71.6—Unverified
#ModelMetricClaimedVerifiedStatus
1BUCTD-preNet-W48 (CID-W32)mAP93.3—Unverified
2CID-W32mAP92.5—Unverified
3BUCTD-CoAM-W48 (DLCRNet)mAP91.6—Unverified
4DLCRNet_ms-graph34mAP89—Unverified
#ModelMetricClaimedVerifiedStatus
18 Stacked Hourglass Network[email protected]78.65—Unverified
22 Stacked Hourglass Network[email protected]77.19—Unverified
3Mask R-CNN[email protected]50.77—Unverified
#ModelMetricClaimedVerifiedStatus
1PAREPA-MPJPE134.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SuperAnimal-AnimalTokenPoseAP86—Unverified