Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows

doi:10.1109/JAS.2023.123456

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows
	Zheyun Qin; Xiankai Lu; Xiushan Nie; Dongfang Liu; Yilong Yin; Wenguan Wang
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2023
卷号	10 期号:5 页码:1192-1208
摘要	We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect, segment and track each instance in a video sequence. Differently from current discriminative tracking-by-detection solutions, our proposed hierarchical structural embedding learning can predict more high-quality masks with accurate boundary details over spatio-temporal space via the normalizing flows. We formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and space. Given the video clip, our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine manner. For the mixing distribution, we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation performance. Comprehensive qualitative, quantitative, and ablation experiments are performed on three representative video instance segmentation benchmarks (i.e., YouTube-VIS₁₉, YouTube-VIS₂₁, and OVIS) and the effectiveness of the proposed method is demonstrated. More impressively, the superior performance of our model on an unsupervised video object segmentation dataset (i.e., DAVIS₁₉) proves its generalizability. Our algorithm implementations are publicly available at https://github.com/zyqin19/HEVis.
关键词	Embedding learning generative model normalizing flows video instance segmentation (VIS)
DOI	10.1109/JAS.2023.123456
引用统计	被引频次：30[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51555
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Zheyun Qin,Xiankai Lu,Xiushan Nie,et al. Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows[J]. IEEE/CAA Journal of Automatica Sinica,2023,10(5):1192-1208.
APA	Zheyun Qin,Xiankai Lu,Xiushan Nie,Dongfang Liu,Yilong Yin,&Wenguan Wang.(2023).Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows.IEEE/CAA Journal of Automatica Sinica,10(5),1192-1208.
MLA	Zheyun Qin,et al."Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows".IEEE/CAA Journal of Automatica Sinica 10.5(2023):1192-1208.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JAS-2022-1528.pdf（42794KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载