# Video Object Segmentation with Re-identification

arXiv: https://arxiv.org/abs/1708.00197 · HTML: https://mlsanity.com/paper/1708.00197/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2017.

## Built on by (most cited first, 6 of 6)

- [FactorMatte: Redefining Video Matting for Re-Composition Tasks](https://mlsanity.com/paper/2211.02145/) (2022)
- [MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentation](https://mlsanity.com/paper/2111.14646/) (2021)
- [Temporally stable video segmentation without video annotations](https://mlsanity.com/paper/2110.08893/) (2021)
- [Box Supervised Video Segmentation Proposal Network](https://mlsanity.com/paper/2202.07025/) (2022)
- [Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation](https://mlsanity.com/paper/2106.03330/) (2021)
- [ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification](https://mlsanity.com/paper/2311.02734/) (2023)

## Abstract (arXiv)

Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an effective mechanism to prevent the target from being lost via adaptive object re-identification. Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module. The former module produces an initial probability map by flow warping while the latter module retrieves missing instances by adaptive matching. With these two modules iteratively applied, our VS-ReID records a global mean (Region Jaccard and Boundary F measure) of 0.699, the best performance in 2017 DAVIS Challenge.