Multi-scale spatio-temporal memory network for semi-supervised video object segmentation
Authors:
- Hui WangHWHui Wang
- Yuqian ZhaoYZYuqian Zhao
- Fan ZhangFan Zhang
- Lingli YuLYLingli Yu
- Chunhua YangCYChunhua Yang
- 11 May 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 642
Abstract
No abstract availableFunding Information
- Key Research and Development Program of Hunan Province of China (2023GK2021)
- Higher Education Discipline Innovation Project (B18059)
- National Key Research and Development Program of China (2022YFE0112300)
- National Natural Science Foundation of China (62272161)
- National Natural Science Foundation of China (62076256)
This publication has 34 references indexed in Scilit:
- Video object segmentation based on multi-level target models and feature integrationNeurocomputing, 2022
- SCWC: Structured channel weight sharing to compress convolutional neural networksInformation Sciences, 2022
- Attributes based skin lesion detection and recognition: A mask RCNN and transfer learning-based deep learning frameworkPattern Recognition Letters, 2021
- Flow Adaptive Video Object SegmentationImage and Vision Computing, 2020
- Lucid Data Dreaming for Video Object SegmentationInternational Journal of Computer Vision, 2019
- CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF2018
- Efficient Video Object Segmentation via Network Modulation2018
- Moving object segmentation for jittery videos, by clustering of stabilized latent trajectoriesImage and Vision Computing, 2017
- One-Shot Video Object Segmentation2017
- Learning Video Object Segmentation from Static Images2017