A memory-based conditional neural process for video instance segmentation

doi:10.1016/j.neucom.2025.131439

Return

A memory-based conditional neural process for video instance segmentation

2025-09-01

DOI：10.1016/j.neucom.2025.131439

Original

Save

View PDF

Abstract

En 中文

• A memory-based conditional neural process. • Reliability modelling for object detection. • Uncertainty-based dynamic training sample selection. • Contrastive instance tracking.

Keywords:

Video instance segmentation

Memory network

Neural processes

Uncertainty

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.