# T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information

arXiv: https://arxiv.org/abs/2104.08029 · HTML: https://mlsanity.com/paper/2104.08029/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Cross-Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/1908.05806/) (2019)
- [Human pose estimation via Convolutional Part Heatmap Regression](https://mlsanity.com/paper/1609.01743/) (2016)
- [RGBD-Dog: Predicting Canine Pose from RGBD Sensors](https://mlsanity.com/paper/2004.07788/) (2020)
- [Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals](https://mlsanity.com/paper/2001.08601/) (2020)
- [ZooBuilder: 2D and 3D Pose Estimation for Quadrupeds Using Synthetic Data](https://mlsanity.com/paper/2009.05389/) (2020)

## Built on by (most cited first, 15 of 15)

- [Unsupervised Keypoints from Pretrained Diffusion Models](https://mlsanity.com/paper/2312.00065/) (2023)
- [OpenApePose: a database of annotated ape photographs for pose estimation](https://mlsanity.com/paper/2212.00741/) (2022)
- [CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming](https://mlsanity.com/paper/2312.08764/) (2023)
- [Video-based automatic lameness detection of dairy cows using pose estimation and multiple locomotion traits](https://mlsanity.com/paper/2401.05202/) (2024)
- [Animal Behavior Analysis Methods Using Deep Learning: A Survey](https://mlsanity.com/paper/2405.14002/) (2024)
- [A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior](https://mlsanity.com/paper/2308.03411/) (2023)
- [Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis](https://mlsanity.com/paper/2410.09312/) (2024)
- [Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance](https://mlsanity.com/paper/2505.18342/) (2025)
- [Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior](https://mlsanity.com/paper/2307.13361/) (2023)
- [3D Pose Estimation of Tomato Peduncle Nodes using Deep Keypoint Detection and Point Cloud](https://mlsanity.com/paper/2311.04699/) (2023)
- [Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes](https://mlsanity.com/paper/2505.15408/) (2025)
- [CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigation](https://mlsanity.com/paper/2507.17727/) (2025)
- [Lameness detection in dairy cows using pose estimation and bidirectional LSTMs](https://mlsanity.com/paper/2508.10643/) (2025)
- [FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation](https://mlsanity.com/paper/2603.16596/) (2026)
- [Promptable Animal Pose Tracking Across Species](https://mlsanity.com/paper/2608.04995/) (2026)

## Abstract (arXiv)

As herd size on dairy farms continues to increase, automatic health monitoring of cows is gaining in interest. Lameness, a prevalent health disorder in dairy cows, is commonly detected by analyzing the gait of cows. A cow's gait can be tracked in videos using pose estimation models because models learn to automatically localize anatomical landmarks in images and videos. Most animal pose estimation models are static, that is, videos are processed frame by frame and do not use any temporal information. In this work, a static deep-learning model for animal-pose-estimation was extended to a temporal model that includes information from past frames. We compared the performance of the static and temporal pose estimation models. The data consisted of 1059 samples of 4 consecutive frames extracted from videos (30 fps) of 30 different dairy cows walking through an outdoor passageway. As farm environments are prone to occlusions, we tested the robustness of the static and temporal models by adding artificial occlusions to the videos.The experiments showed that, on non-occluded data, both static and temporal approaches achieved a Percentage of Correct Keypoints (PCKh@0.2) of 99%. On occluded data, our temporal approach outperformed the static one by up to 32.9%, suggesting that using temporal data was beneficial for pose estimation in environments prone to occlusions, such as dairy farms. The generalization capabilities of the temporal model was evaluated by testing it on data containing unknown cows (cows not present in the training set). The results showed that the average PCKh@0.2 was of 93.8% on known cows and 87.6% on unknown cows, indicating that the model was capable of generalizing well to new cows and that they could be easily fine-tuned to new herds. Finally, we showed that with harder tasks, such as occlusions and unknown cows, a deeper architecture was more beneficial.