# Transferring Dense Pose to Proximal Animal Classes

arXiv: https://arxiv.org/abs/2003.00080 · HTML: https://mlsanity.com/paper/2003.00080/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2020.

## Built on by (most cited first, 23 of 23)

- [Seeing biodiversity: perspectives in machine learning for wildlife conservation](https://mlsanity.com/paper/2110.12951/) (2021)
- [MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing](https://mlsanity.com/paper/2305.10345/) (2023)
- [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information](https://mlsanity.com/paper/2203.15536/) (2022)
- [CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose](https://mlsanity.com/paper/2206.11752/) (2022)
- [Triple-stream Deep Metric Learning of Great Ape Behavioural Actions](https://mlsanity.com/paper/2301.02642/) (2023)
- [Discovering Relationships between Object Categories via Universal Canonical Maps](https://mlsanity.com/paper/2106.09758/) (2021)
- [3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking](https://mlsanity.com/paper/2308.15316/) (2023)
- [OpenApePose: a database of annotated ape photographs for pose estimation](https://mlsanity.com/paper/2212.00741/) (2022)
- [UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model](https://mlsanity.com/paper/2110.15267/) (2021)
- [Reconstructing Animals and the Wild](https://mlsanity.com/paper/2411.18807/) (2024)
- [UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation](https://mlsanity.com/paper/2512.07831/) (2025)
- [Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data](https://mlsanity.com/paper/2208.13944/) (2022)
- [DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension](https://mlsanity.com/paper/2109.00033/) (2021)
- [Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise](https://mlsanity.com/paper/2111.02450/) (2021)
- [Future of Edge AI in biodiversity monitoring](https://mlsanity.com/paper/2602.13496/) (2026)
- [Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation](https://mlsanity.com/paper/2108.13258/) (2021)
- [ProcSim: Proxy-based Confidence for Robust Similarity Learning](https://mlsanity.com/paper/2311.00668/) (2023)
- [Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis](https://mlsanity.com/paper/2410.09312/) (2024)
- [Semi-supervised Dense Keypoints Using Unlabeled Multiview Images](https://mlsanity.com/paper/2109.09299/) (2021)
- [Incremental Learning for Animal Pose Estimation using RBF k-DPP](https://mlsanity.com/paper/2110.13598/) (2021)
- [Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning](https://mlsanity.com/paper/2111.08259/) (2021)
- [RatBodyFormer: Rat Body Surface from Keypoints](https://mlsanity.com/paper/2412.09599/) (2024)
- [Overcoming the Domain Gap in Neural Action Representations](https://mlsanity.com/paper/2112.01176/) (2021)

## Abstract (arXiv)

Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each case makes this strategy impractical, despite important applications in natural conservation, science and business. We show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by (1) establishing a DensePose model for the new animal which is also geometrically aligned to humans (2) introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, (3) finding which combination of known classes can be transferred most effectively to the new animal and (4) using self-calibrated uncertainty heads to generate pseudo-labels graded by quality for training a model for this class. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach, showing excellent transfer learning performance.