Multi-scale hypergraph-based feature alignment network for cell localization
Cell localization in medical image analysis is a challenging task due to the significant
variation in cell shape, size and color. Existing localization methods continue to tackle these …
variation in cell shape, size and color. Existing localization methods continue to tackle these …
Purity skeleton dynamic hypergraph neural network
Y Wang, X Yang, Q Sun, Y Qian, Q Guo - Neurocomputing, 2024 - Elsevier
Recently, in the field of Hypergraph Neural Networks (HGNNs), the effectiveness of dynamic
hypergraph construction has been validated, which aims to reduce structural noise within …
hypergraph construction has been validated, which aims to reduce structural noise within …
Lite-UNet: A lightweight and efficient network for cell localization
Cell localization constitutes a fundamental research domain within the realm of pathology
image analysis, with its core objective being the precise identification of cell spatial …
image analysis, with its core objective being the precise identification of cell spatial …
CrowdGraph: Weakly supervised crowd counting via pure graph neural network
Most existing weakly supervised crowd counting methods utilize Convolutional Neural
Networks (CNN) or Transformer to estimate the total number of individuals in an image …
Networks (CNN) or Transformer to estimate the total number of individuals in an image …
Multi-granularity hypergraph-guided transformer learning framework for visual classification
J Jiang, Z Chen, F Lei, L Xu, J Huang, X Yuan - The Visual Computer, 2024 - Springer
Fine-grained single-label classification tasks aim to distinguish highly similar categories but
often overlook inter-category relationships. Hierarchical multi-granularity visual classification …
often overlook inter-category relationships. Hierarchical multi-granularity visual classification …
Few-shot Object Localization
Existing object localization methods are tailored to locate specific classes of objects, relying
heavily on abundant labeled data for model optimization. However, acquiring large amounts …
heavily on abundant labeled data for model optimization. However, acquiring large amounts …
Cross‐modal fusion encoder via graph neural network for referring image segmentation
Y Zhang, Y Zhang, X Piao, P Yuan, Y Hu… - IET Image …, 2024 - Wiley Online Library
Referring image segmentation identifies the object masks from images with the guidance of
input natural language expressions. Nowadays, many remarkable cross‐modal decoder are …
input natural language expressions. Nowadays, many remarkable cross‐modal decoder are …
Glance to count: Learning to rank with anchors for weakly-supervised crowd counting
Crowd image is arguably one of the most laborious data to annotate. In this paper, we
devote to reduce the massive demand of densely labeled crowd data, and propose a novel …
devote to reduce the massive demand of densely labeled crowd data, and propose a novel …
[HTML][HTML] A Weakly Supervised Crowd Counting Method via Combining CNN and Transformer
Y Cai, D Zhang - Electronics, 2024 - mdpi.com
During the past five years, there has been an increasing trend of weakly supervised crowd
counting methods being developed since such methods just rely on count-level annotations …
counting methods being developed since such methods just rely on count-level annotations …
Few‐shot object detection based on global context and implicit knowledge decoupled head
S Li, G Yang, X Liu, K Huang, Y Liu - IET Image Processing, 2024 - Wiley Online Library
The acquisition cycle of remote sensing images is slow, and the labelling process
encounters challenges, which have become prominent with the rapid development of …
encounters challenges, which have become prominent with the rapid development of …