# Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation

arXiv: https://arxiv.org/abs/1809.01125 · HTML: https://mlsanity.com/paper/1809.01125/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2018.

## Built on by (most cited first, 17 of 17)

- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Deformable Sprites for Unsupervised Video Decomposition](https://mlsanity.com/paper/2204.07151/) (2022)
- [VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation](https://mlsanity.com/paper/2308.14710/) (2023)
- [Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation](https://mlsanity.com/paper/2104.04782/) (2021)
- [A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.09341/) (2022)
- [Spatiotemporal Data Mining: A Survey on Challenges and Open Problems](https://mlsanity.com/paper/2103.17128/) (2021)
- [Optical Flow Estimation from a Single Motion-blurred Image](https://mlsanity.com/paper/2103.02996/) (2021)
- [Event-Free Moving Object Segmentation from Moving Ego Vehicle](https://mlsanity.com/paper/2305.00126/) (2023)
- [Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering](https://mlsanity.com/paper/2306.12048/) (2023)
- [Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2501.07806/) (2025)
- [InstMove: Instance Motion for Object-centric Video Segmentation](https://mlsanity.com/paper/2303.08132/) (2023)
- [Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots](https://mlsanity.com/paper/2304.01430/) (2023)
- [Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation](https://mlsanity.com/paper/2105.01553/) (2021)
- [DAVOS: Semi-Supervised Video Object Segmentation via Adversarial Domain Adaptation](https://mlsanity.com/paper/2105.10201/) (2021)
- [Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery](https://mlsanity.com/paper/2109.00885/) (2021)
- [Investigation of Frame Differences as Motion Cues for Video Object Segmentation](https://mlsanity.com/paper/2503.09132/) (2025)
- [Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision](https://mlsanity.com/paper/2609.39785/) (2026)

## Abstract (arXiv)

Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. To address these challenges for unsupervised video segmentation, we develop a novel saliency estimation technique as well as a novel neighborhood graph, based on optical flow and edge cues. Our approach leads to significantly better initial foreground-background estimates and their robust as well as accurate diffusion across time. We evaluate our proposed algorithm on the challenging DAVIS, SegTrack v2 and FBMS-59 datasets. Despite the usage of only a standard edge detector trained on 200 images, our method achieves state-of-the-art results outperforming deep learning based methods in the unsupervised setting. We even demonstrate competitive results comparable to deep learning based methods in the semi-supervised setting on the DAVIS dataset.