Abstract | ||
---|---|---|
In this work, we address the task of semi-supervised video object segmentation(VOS) and explore how to make efficient use of video property to tackle the challenge of semi-supervision. We propose a novel pipeline called State-Aware Tracker(SAT), which can produce accurate segmentation results with real-time speed. For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet. For more stable and robust performance over video sequences, SAT gets awareness for each state and makes self-adaptation via two feedback loops. One loop assists SAT in generating more stable tracklets. The other loop helps to construct a more robust and holistic target representation. SAT achieves a promising result of 72.3% J&F mean with 39 FPS on DAVIS2017-Val dataset, which shows a decent trade-off between efficiency and accuracy. Code will be released at github.com/MegviiDetection/video_analyst. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CVPR42600.2020.00940 | CVPR |
DocType | Citations | PageRank |
Conference | 2 | 0.38 |
References | Authors | |
15 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Xi | 1 | 4 | 1.87 |
Li Zuoxin | 2 | 16 | 2.61 |
Yuan Ye | 3 | 2 | 0.38 |
Gang Yu | 4 | 382 | 19.85 |
Shen Jianxin | 5 | 27 | 5.63 |
Qi Donglian | 6 | 38 | 7.99 |