Sketch-based Video Object Segmentation: Benchmark and Analysis
Ruolin Yang (Beijing University of Posts and Telecommunications),* Da Li (Samsung), Conghui Hu (National University of Singapore), Timothy Hospedales (Edinburgh University), Honggang Zhang (Beijing University of Posts and Telecommunications), Yi-Zhe Song (University of Surrey)
The 34th British Machine Vision Conference
Abstract
Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask. However, language expressions can sometimes be vague in conveying an intended concept and ambiguous when similar objects in one frame are hard to distinguish by language. Meanwhile, photo masks are costly to annotate and less practical to provide in a real application. This paper introduces a new task of sketch-based video object segmentation, an associated benchmark, and a strong baseline. Our benchmark includes three datasets, Sketch-DAVIS16, Sketch-DAVIS17 and Sketch-YouTube-VOS, which exploit human-drawn sketches as an informative yet low-cost reference for video object segmentation. We take advantage of STCN, a popular baseline of semi-supervised VOS task, and evaluate what the most effective design for incorporating a sketch reference is. Experimental results show sketch is more effective yet annotation-efficient than other references, such as photo masks, language and scribble.Video
Citation
@inproceedings{Yang_2023_BMVC,
author = {Ruolin Yang and Da Li and Conghui Hu and Timothy Hospedales and Honggang Zhang and Yi-Zhe Song},
title = {Sketch-based Video Object Segmentation: Benchmark and Analysis},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0540.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by