# MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification

arXiv: https://arxiv.org/abs/2603.04314 · HTML: https://mlsanity.com/paper/2603.04314/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning](https://mlsanity.com/paper/2006.09205/) (2020)
- [SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification](https://mlsanity.com/paper/2211.10307/) (2022)
- [SealID: Saimaa ringed seal re-identification dataset](https://mlsanity.com/paper/2206.02260/) (2022)
- [Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset](https://mlsanity.com/paper/2105.01938/) (2021)
- [Multi-views Embedding for Cattle Re-identification](https://mlsanity.com/paper/1902.04886/) (2019)
- [Learning landmark guided embeddings for animal re-identification](https://mlsanity.com/paper/2001.02801/) (2020)
- [Animal Identification with Independent Foreground and Background Modeling](https://mlsanity.com/paper/2408.12930/) (2024)
- [Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data](https://mlsanity.com/paper/2208.13944/) (2022)
- [Learning Part Segmentation from Synthetic Animals](https://mlsanity.com/paper/2311.18661/) (2023)
- [Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment](https://mlsanity.com/paper/2405.13781/) (2024)
- [CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx](https://mlsanity.com/paper/2506.04931/) (2025)
- [Unsupervised Pelage Pattern Unwrapping for Animal Re-identification](https://mlsanity.com/paper/2506.15369/) (2025)
- [Holstein-Friesian Re-Identification using Multiple Cameras and Self-Supervision on a Working Farm](https://mlsanity.com/paper/2410.12695/) (2024)
- [ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data](https://mlsanity.com/paper/2408.10831/) (2024)
- [SPOTS-10: Animal Pattern Benchmark Dataset for Machine Learning Algorithms](https://mlsanity.com/paper/2410.21044/) (2024)

## Built on by (most cited first, 3 of 3)

- [3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification](https://mlsanity.com/paper/2604.26520/) (2026)
- [Centering Ecological Goals in Automated Identification of Individual Animals](https://mlsanity.com/paper/2604.20626/) (2026)
- [WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife](https://mlsanity.com/paper/2606.21309/) (2026)

## Abstract (arXiv)

Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of 1,000 cattle individuals captured from 128 uniformly sampled viewpoints (128,000 annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO.