# BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames

arXiv: https://arxiv.org/abs/1903.11779 · HTML: https://mlsanity.com/paper/1903.11779/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 14 of 14)

- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [XMem++: Production-level Video Segmentation From Few Annotated Frames](https://mlsanity.com/paper/2307.15958/) (2023)
- [Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier](https://mlsanity.com/paper/2112.12402/) (2021)
- [Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps](https://mlsanity.com/paper/2104.10386/) (2021)
- [Learning the What and How of Annotation in Video Object Segmentation](https://mlsanity.com/paper/2311.04414/) (2023)
- [Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild](https://mlsanity.com/paper/2103.10391/) (2021)
- [Appearance-Based Refinement for Object-Centric Motion Segmentation](https://mlsanity.com/paper/2312.11463/) (2023)
- [FAR: Fourier Aerial Video Recognition](https://mlsanity.com/paper/2203.10694/) (2022)
- [U-LanD: Uncertainty-Driven Video Landmark Detection](https://mlsanity.com/paper/2102.01586/) (2021)
- [Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment](https://mlsanity.com/paper/2210.08054/) (2022)
- [Correlation-aware active learning for surgery video segmentation](https://mlsanity.com/paper/2311.08811/) (2023)
- [Burst Image Super-Resolution with Base Frame Selection](https://mlsanity.com/paper/2406.17869/) (2024)
- [TagMe: GPS-Assisted Automatic Object Annotation in Videos](https://mlsanity.com/paper/2103.13428/) (2021)
- [Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track](https://mlsanity.com/paper/2603.23788/) (2026)

## Abstract (arXiv)

Semi-supervised video object segmentation has made significant progress on real and challenging videos in recent years. The current paradigm for segmentation methods and benchmark datasets is to segment objects in video provided a single annotation in the first frame. However, we find that segmentation performance across the entire video varies dramatically when selecting an alternative frame for annotation. This paper address the problem of learning to suggest the single best frame across the video for user annotation-this is, in fact, never the first frame of video. We achieve this by introducing BubbleNets, a novel deep sorting network that learns to select frames using a performance-based loss function that enables the conversion of expansive amounts of training examples from already existing datasets. Using BubbleNets, we are able to achieve an 11% relative improvement in segmentation performance on the DAVIS benchmark without any changes to the underlying method of segmentation.