Corpus ID: 237352914

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

  title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
  author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
  • Hang Yu, Yufei Xu, +3 authors D. Tao
  • Published 2021
  • Computer Science
  • ArXiv
Accurate animal pose estimation is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. Previous works only focus on specific animals while ignoring the diversity of animal species, limiting the generalization ability. In this paper, we propose AP-10K, the first large-scale benchmark for general animal pose estimation, to facilitate the research in animal pose estimation. AP-10K consists of 10,015… Expand

Figures and Tables from this paper


Cross-Domain Adaptation for Animal Pose Estimation
This paper proposed a novel cross-domain adaptation method to transform the animal pose knowledge from labeled animal classes to unlabeled animal classes, and uses the modest animal pose dataset to adapt learned knowledge to multiple animals species. Expand
Fast animal pose estimation using deep neural networks
This work validated LEAP using videos of freely behaving fruit flies and tracked 32 distinct points to describe the pose of the head, body, wings and legs, with an error rate of<3% of body length and demonstrated LEAP’s applicability for unsupervised behavioral classification. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models. Expand
DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
A new easy-to-use software toolkit, DeepPoseKit, is introduced that addresses animal pose estimation problems using an efficient multi-scale deep-learning model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoint locations with subpixel precision. Expand
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene. Expand
CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark
A novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms and results on MSCOCO dataset demonstrate the generalization ability of the proposed method. Expand
Pose2Seg: Detection Free Human Instance Segmentation
This paper introduces a new benchmark "Occluded Human (OCHuman)", which focuses on occluded humans with comprehensive annotations including bounding-box, human pose and instance masks, and demonstrates that this pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion. Expand
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly
A new zero-shot learning dataset is proposed, the Animals with Attributes 2 (AWA2) dataset which is made publicly available both in terms of image features and the images themselves and compares and analyzes a significant number of the state-of-the-art methods in depth. Expand
Towards High Performance Human Keypoint Detection
This paper proposes a cascaded context mixer (CCM), which efficiently integrates spatial and channel context information and progressively refines them, and develops a hard-negative person detection mining strategy and a joint-training strategy by exploiting abundant unlabeled data. Expand
MacaquePose: A novel ‘in the wild’ macaque monkey pose dataset for markerless motion capture
The MacaquePose, a novel open dataset with manually labeled body part positions for macaques in naturalistic scenes, consisting of >13,000 images, refined by researchers, shows that the pose estimation performance of an artificial neural network trained with the dataset is close to that of a human-level. Expand