22 Result(s)
-
Article
The image and ground truth dataset of Mongolian movable-type newspapers for text recognition
OCR approaches have been widely advanced in recent years thanks to the resurgence of deep learning. However, to the best of our knowledge, there is little work on Mongolian movable-type document recognition. O...
-
Chapter and Conference Paper
MnTTS2: An Open-Source Multi-speaker Mongolian Text-to-Speech Synthesis Dataset
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongolia Autonomous Region and a rep...
-
Chapter and Conference Paper
A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion
Cyrillic and Traditional Mongolian are the two main members of the Mongolian writing system. The Cyrillic-Traditional Mongolian Bidirectional Conversion (CTMBC) task includes two conversion processes, includin...
-
Chapter and Conference Paper
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been pro...
-
Chapter and Conference Paper
End-to-End Large-Scale Image Retrieval Network with Convolution and Vision Transformers
There has been significant progress in content-based image retrieval with the development of convolutional neural networks and visual transformers. However, there are semantic gaps between high-level semantic ...
-
Chapter and Conference Paper
Panoptic-DLA: Document Layout Analysis of Historical Newspapers Based on Proposal-Free Panoptic Segmentation Model
In this paper, we introduce a novel historical newspaper layout analysis model named Panoptic-DLA. Different from the previous works regarding layout analysis as a separate object detection or semantic segment...
-
Article
Impulse Noise Detector Performance Measure Based on Intensity Volume
An accurate detector performance evaluation method provides a fair comparison platform and can also support in parameter optimization for existing Impulse noise detectors in the applications of medical imaging...
-
Chapter and Conference Paper
Infrared Small Target Recognition with Improved Particle Filtering Based on Feature Fusion
Aiming at the problem of tracking weak targets in different scenarios, an improved particle tracking method is proposed. This paper firstly uses background prediction and extracts the gray and motion features ...
-
Chapter and Conference Paper
Morphological Knowledge Guided Mongolian Constituent Parsing
Mongolian constituent parsing is a challenging task due to lack of hand-annotated corpus and rich morphological varying. This paper takes a self-attention neural network to deal with Mongolian constituent pars...
-
Chapter and Conference Paper
Micro Heater with Low Temperature Coefficient of Resistance for ICF Target
A micro heater with low temperature coefficient of resistance (TCR) at liquid hydrogen temperature was designed and fabricated by micro fabrication technology. The NiCr heater annealed in N2 at 250 °C for 9 min a...
-
Chapter and Conference Paper
Building Mongolian TTS Front-End with Encoder-Decoder Model by Using Bridge Method and Multi-view Features
In the context of text-to-speech systems (TTS), a front-end is a critical step for extracting linguistic features from given input text. In this paper, we propose a Mongolian TTS front-end which joint training...
-
Chapter and Conference Paper
A Natural Scene Text Extraction Approach Based on Generative Adversarial Learning
Extracting textual information embodied in natural scenes is a very challenge task, and has a great influence on the performance of the following text recognition and understanding. It can be seen as an image...
-
Chapter and Conference Paper
Mongolian Word Segmentation Based on Three Character Level Seq2Seq Models
Mongolian word segmentation is splitting the Mongolian words into roots and suffixes. It plays an important role in Mongolian related natural language processing tasks. To improve performance and avoid the ted...
-
Chapter and Conference Paper
Phonologically Aware BiLSTM Model for Mongolian Phrase Break Prediction with Attention Mechanism
Phrase break prediction is the first and most important component in increasing naturalness and intelligibility of text-to-speech (TTS) systems. Most works rely on language specific resources, large annotated ...
-
Article
Single sample per person face recognition with KPCANet and a weighted voting scheme
Most current methods of facial recognition rely on the condition of having multiple samples per person available for feature extraction. In practical applications, however, only one sample may be available for...
-
Article
A knowledge-based recognition system for historical Mongolian documents
This paper proposes a knowledge-based system to recognize historical Mongolian documents in which the words exhibit remarkable variation and character overlap**. According to the characteristics of Mongolian...
-
Chapter and Conference Paper
Video Anomaly Detection Based on Adaptive Multiple Auto-Encoders
Anomaly detection in surveillance videos is a challenging problem in computer vision community. In this paper, a novel unsupervised learning framework is proposed to detect and localize abnormal events in real...
-
Chapter and Conference Paper
Enhancing the Mongolian Historical Document Recognition System with Multiple Knowledge-Based Strategies
This paper describes recent work on integrating multiple strategies to improve the performance of the Mongolian historical document recognition system which utilize the segmentation-based scheme. We analyze th...
-
Chapter and Conference Paper
Character Segmentation for Classical Mongolian Words in Historical Documents
There are many classical Mongolian historical documents which are reserved in image form, and as a result it is inconvenient for us to search and mining the desired content. In order to facilitate the word rec...
-
Chapter and Conference Paper
A Convergent Incoherent Dictionary Learning Algorithm for Sparse Coding
Recently, sparse coding has been widely used in many applications ranging from image recovery to pattern recognition. The low mutual coherence of a dictionary is an important property that ensures the optimali...
