5 papers
Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation
Zhigang Yang, Huiguang Yao, Linmao Tian +3
Referring remote sensing image segmentation (RRSIS) is a challenging multimodal task that requires accurate localization and pixel-level segmentation of targets specified by natura…
A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
Haoxuan Ding, Qi Wang, Junyu Gao +1
Traditional license plate detection and recognition models are often trained on closed datasets, limiting their ability to handle the diverse license plate formats across different…
Cross-Modal Spherical Aggregation for Weakly Supervised Remote Sensing Shadow Removal
Kaichen Chi, Wei Jing, Junjie Li +2
Remote sensing shadow removal, which aims to recover contaminated surface information, is tricky since shadows typically display overwhelmingly low illumination intensities. In con…
Text-only Synthesis for Image Captioning
Qing Zhou, Junlin Huang, Qiang Li +2
From paired image-text training to text-only training for image captioning, the pursuit of relaxing the requirements for high-cost and large-scale annotation of good quality data r…
Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
Yuyu Jia, Wei Huang, Junyu Gao +2
Few-shot segmentation (FSS) for remote sensing (RS) imagery leverages supporting information from limited annotated samples to achieve query segmentation of novel classes. Previous…