Related papers: ShufaNet: Classification method for calligraphers …
Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph annotation or labeling, we face a severe graph label-scarcity…
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform…
Different from the conventional deep learning work based on an images content in computer vision, deep steganalysis is an art to detect the secret information embedded in an image via deep learning, pose challenge of detection weak…
The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…
Dysgraphia is a learning disorder that affects handwriting abilities, making it challenging for children to write legibly and consistently. Early detection and monitoring are crucial for providing timely support and interventions. This…
Network anomaly detection aims to find network elements (e.g., nodes, edges, subgraphs) with significantly different behaviors from the vast majority. It has a profound impact in a variety of applications ranging from finance, healthcare to…
Meta-learning methods have been widely used in few-shot named entity recognition (NER), especially prototype-based methods. However, the Other(O) class is difficult to be represented by a prototype vector because there are generally a large…
We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic…
Currently, owing to the ubiquity of mobile devices, online handwritten Chinese character recognition (HCCR) has become one of the suitable choice for feeding input to cell phones and tablet devices. Over the past few years, larger and…
Layout analysis is a task of uttermost importance in ancient handwritten document analysis and represents a fundamental step toward the simplification of subsequent tasks such as optical character recognition and automatic transcription.…
Boundary Representations (B-Reps) are the industry standard in 3D Computer Aided Design/Manufacturing (CAD/CAM) and industrial design due to their fidelity in representing stylistic details. However, they have been ignored in the 3D style…
Efficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS). Vanilla NAS evaluates each architecture by training from scratch, which gives the true performance…
Deep convolutional networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwritten Chinese character recognition(HCCR) problem through learning discriminative features…
Image modality recognition is essential for efficient imaging workflows in current clinical environments, where multiple imaging modalities are used to better comprehend complex diseases. Emerging biomarkers from novel, rare modalities are…
Deep Convolutional Neural Networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and…
Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries…
As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a crucial aspect of model deployment. As a result, model…
Existing high-resolution satellite image forgery localization methods rely on patch-based or downsampling-based training. Both of these training methods have major drawbacks, such as inaccurate boundaries between pristine and forged…
The challenge of automatically synthesizing high-quality vector fonts, particularly for writing systems (e.g., Chinese) consisting of huge amounts of complex glyphs, remains unsolved. Existing font synthesis techniques fall into two…
Our research focuses on few-shot fine-grained image classification, which faces two major challenges: appearance similarity of fine-grained objects and limited number of samples. To preserve the appearance details of images, traditional…