Self-Supervised joint flow and depth estimation via Multi-Cue uncertainty modeling.

Saved in:
Bibliographic Details
Title: Self-Supervised joint flow and depth estimation via Multi-Cue uncertainty modeling.
Authors: Abdein R; College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China. Electronic address: rokiaabdeen@hrbeu.edu.cn., Li W; College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China; Modeling and Emulation in E-Government National Engineering Laboratory, Harbin Engineering University, Harbin, 150001, China. Electronic address: weil.li@hrbeu.edu.cn., Chen Y; College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China. Electronic address: chenyidan@hrbeu.edu.cn., Li C; College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China. Electronic address: chli@hrbeu.edu.cn., Helal S; Computer Science and Engineering Department, University of Bologna, Bologna, Italy. Electronic address: sumi.helal@unibo.it., Youssef M; Department of Computer Science and Engineering, The American University in Cairo, Cairo, Egypt. Electronic address: moustafa-youssef@aucegypt.edu.
Source: Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2026 Jul; Vol. 199, pp. 108771. Date of Electronic Publication: 2026 Feb 24.
Publication Type: Journal Article
Journal Info: Publisher: Pergamon Press Country of Publication: United States NLM ID: 8805018 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-2782 (Electronic) Linking ISSN: 08936080 NLM ISO Abbreviation: Neural Netw Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:1879-2782
DOI:10.1016/j.neunet.2026.108771