# Articulated motion discovery using pairs of trajectories

arXiv: https://arxiv.org/abs/1411.7883 · HTML: https://mlsanity.com/paper/1411.7883/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2014.

## Built on by (most cited first, 13 of 13)

- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [A Unified Framework for Domain Adaptive Pose Estimation](https://mlsanity.com/paper/2204.00172/) (2022)
- [Learning monocular 3D reconstruction of articulated categories from motion](https://mlsanity.com/paper/2103.16352/) (2021)
- [Weakly Supervised Keypoint Discovery](https://mlsanity.com/paper/2109.13423/) (2021)
- [MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection](https://mlsanity.com/paper/2302.04589/) (2023)
- [Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis](https://mlsanity.com/paper/2410.09312/) (2024)
- [Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals](https://mlsanity.com/paper/2508.16062/) (2025)
- [Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning](https://mlsanity.com/paper/2111.08259/) (2021)
- [Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior](https://mlsanity.com/paper/2307.13361/) (2023)
- [Domain adaptive pose estimation via multi-level alignment](https://mlsanity.com/paper/2404.14885/) (2024)
- [Video-based estimation of pain indicators in dogs](https://mlsanity.com/paper/2209.13296/) (2022)
- [Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?](https://mlsanity.com/paper/2306.01706/) (2023)
- [Self-supervised Extraction of Human Motion Structures via Frame-wise Discrete Features](https://mlsanity.com/paper/2309.05972/) (2023)

## Abstract (arXiv)

We propose an unsupervised approach for discovering characteristic motion patterns in videos of highly articulated objects performing natural, unscripted behaviors, such as tigers in the wild. We discover consistent patterns in a bottom-up manner by analyzing the relative displacements of large numbers of ordered trajectory pairs through time, such that each trajectory is attached to a different moving part on the object. The pairs of trajectories descriptor relies entirely on motion and is more discriminative than state-of-the-art features that employ single trajectories. Our method generates temporal video intervals, each automatically trimmed to one instance of the discovered behavior, and clusters them by type (e.g., running, turning head, drinking water). We present experiments on two datasets: dogs from YouTube-Objects and a new dataset of National Geographic tiger videos. Results confirm that our proposed descriptor outperforms existing appearance- and trajectory-based descriptors (e.g., HOG and DTFs) on both datasets and enables us to segment unconstrained animal video into intervals containing single behaviors.