检索结果-内蒙古大学图书馆

Automatic classification of cancerous tissue in laserendomicroscopy images of the oral cavity using deep learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Aubreville, Marc Knipfer, Christian Oetter, Nicolai Jaremenko, Christian Rodner, Erik Denzler, Joachim Bohr, Christopher Neumann, Helmut Stelzle, Florian Maier, Andreas Pattern Recognition Lab Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Department of Oral and Maxillofacial Surgery University Medical Center Hamburg-Eppendorf Germany Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Department of Oral and Maxillofacial Surgery University Medical Center Erlangen Friedrich-Alexander- Universität Erlangen-Nürnberg Germany Computer Vision Group Friedrich-Schiller-Universität Jena Germany Department of Otorhinolaryngology Head and Neck Surgery University Medical Center Erlangen Friedrich-Alexander-Universität Erlangen-Nürnberg Germany First Department of Internal Medicine University Medical Center Mainz Johannes Gutenberg-Universität Mainz Germany

Oral Squamous Cell Carcinoma (OSCC) is a common type of cancer of the oral epithelium. Despite their high impact on mortality, sufficient screening methods for early diagnosis of OSCC often lack accuracy and thus OSCCs are mostly diagnosed at a late stage. Early detection and accurate outline estimation of OSCCs would lead to a better curative outcome and an reduction in recurrence rates after surgical treatment. Confocal Laser Endomicroscopy (CLE) records sub-surface micro-anatomical images for in vivo cell structure analysis. Recent CLE studies showed great prospects for a reliable, real-time ultrastructural imaging of OSCC in situ. We present and evaluate a novel automatic approach for a highly accurate OSCC diagnosis using deep learning technologies on CLE images. The method is compared against textural feature-based machine learning approaches that represent the current state of the art. For this work, CLE image sequences (7894 images) from patients diagnosed with OSCC were obtained from 4 specific locations in the oral cavity, including the OSCC lesion. The present approach is found to outperform the state of the art in CLE image recognition with an area under the curve (AUC) of 0.96 and a mean accuracy of 88.3 % (sensitivity 86.6 %, specificity 90 %). Copyright © 2017, The Authors. All rights reserved.

关键词： Diagnosis

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiaozhi Chen, Yulin Ding, Ning Peng, Hao Wang, Zimu Lin, Yankai Han, Xu Hou, Lei Li, Juanzi Liu, Zhiyuan Li, Peng Zhou, Jie Department of Computer Science and Technology BNRist China Shenzhen International Graduate School China THU-Siemens Ltd. China Joint Research Center for Industrial Intelligence and IoT China Tsinghua University Beijing China Xi’an Jiaotong-Liverpool University Suzhou China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Pattern Recognition Center WeChat AI Tencent Inc China

The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation extraction (ERE) tasks: (1) Small scale. Due to the annotation complexity, the data scale of existing datasets is limited, which cannot well train and evaluate data-hungry models. (2) Absence of unified annotation. Different types of event relations naturally interact with each other, but existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions. To address these issues, we construct a unified large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances. The dataset and source codes can be obtained from https://***/THU-KEG/MAVEN-ERE. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

Finger in Camera Speaks Everything: Unconstrained Air-Writing for Real-World

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Meiqi Huang, Kaiqi Cai, Yuanqiang Hu, Shiyu Zhao, Yuzhong Wang, Weiqiang School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Beijing University of Posts and Telecommunications Beijing100876 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Center for Research on Intelligent System and Engineering Institute of Automation Chinese Academy of Sciences Beijing100190 China Center for Research on Intelligent System and Engineering National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

Air-writing is a challenging task that combines the fields of computer vision and natural language processing, offering an intuitive and natural approach for human-computer interaction. However, current air-writing solutions face two primary challenges: (1) their dependency on complex sensors (e.g., Radar, EEGs and others) for capturing precise handwritten trajectories, and (2) the absence of a video-based air-writing dataset that covers a comprehensive vocabulary range. These limitations impede their practicality in various real-world scenarios, including the use on devices like iPhones and laptops. To tackle these challenges, we present the groundbreaking air-writing Chinese character video dataset (AWCV-100K-UCAS2024), serving as a pioneering benchmark for video-based air-writing. This dataset captures handwritten trajectories in various real-world scenarios using commonly accessible RGB cameras, eliminating the need for complex sensors. AWCV-100K-UCAS2024 includes 8.8 million video frames, encompassing the complete set of 3,755 characters from the GB2312-80 level-1 set (GB1). Furthermore, we introduce our baseline approach, the video-based character recognizer (VCRec). VCRec adeptly extracts fingertip features from sparse visual cues and employs a spatio-temporal sequence module for analysis. Experimental results showcase the superior performance of VCRec compared to existing models in recognizing air-written characters, both quantitatively and qualitatively. This breakthrough paves the way for enhanced human-computer interaction in real-world contexts. Moreover, our approach leverages affordable RGB cameras, enabling its applicability in a diverse range of scenarios. The code and data examples will be made public at https://***/wmeiqi/AWCV. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

ChaLearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on pattern recognition (ICPR) 2016 and International Conference on computer vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

Multi-lingual Handwriting Recovery Framework based on Convolutional Denoising Autoencoder with Attention model

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Rabhi, Besma Elbaati, Abdelkarim Boubaker, Houcine Pal, Umapada Alimi, Adel M. University of Sfax National Engineering School of Sfax REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Sfax3038 Tunisia University of Monastir Higher Institute of Applied Sciences and Technology of Mahdia REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Mahdia5121 Tunisia Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa

For several decades, the offline handwriting recognition problem has escaped a satisfactory solution. In the field of online recognition, researchers have had more successful performance, but the ability to extract dynamic information from static images has not been well explored yet. In this paper, we introduce a novel multi-lingual word handwriting recovery framework based on a convolutional denoising autoencoder with an attention model for pen up / down, velocity and temporal order recovery. The proposed framework consists of extracting robust features from a handwriting image using a stacked denoising autoencoder and an encoder Bidirectional Gated Recurrent Unit (BGRU) model. Then, the obtained vectors are decoded to produce an online script with dynamic characteristics using a BGRU with temporal attention. Evaluation is done on a Latin and Arabic Online and offline handwriting character / word databases and the proposed framework achieves high competitive results. To the best of our knowledge, this is the first work of its kind. © 2022, CC BY.

关键词： Recovery

A Survey of the Self Supervised Learning Mechanisms for vision Transformers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Khan, Asifullah Sohail, Anabia Fiaz, Mustansar Hassan, Mehdi Afridi, Tariq Habib Marwat, Sibghat Ullah Munir, Farzeen Ali, Safdar Naseem, Hannan Zaheer, Muhammad Zaigham Ali, Kamran Sultana, Tangina Tanoli, Ziaurrehman Akhter, Naeem Pattern Recognition Lab DCIS PIEAS Nilore Islamabad45650 Pakistan PIEAS Nilore Islamabad45650 Pakistan Deep Learning Lab Center for Mathematical Sciences PIEAS Nilore Islamabad45650 Pakistan Center of Secure Cyber-Physical Security Systems Khalifa University Abu Dhabi United Arab Emirates IBM Research United States Department of Computer Science Air University Islamabad Pakistan Department of Computer Science and Engineering Kyung Hee University Global Campus 1732 Gyeonggi-do Yongin17104 Korea Republic of Department of Electrical Engineering and Automation Aalto University Finland Finnish Center of Artificial Center Finland Faculty of Engineering and Green Technology Universiti Tunku Abdul Rahman Malaysia Computer Vision Department Mohamed Bin Zayed University of Artificial Intelligence United Arab Emirates Karachi Pakistan Department of Electronics and Communication Engineering Hajee Mohammad Danesh Science and Technology University Bangladesh HiLIFE University of Helsinki Finland

vision Transformers (ViTs) have recently demonstrated remarkable performance in computer vision tasks. However, their parameter-intensive nature and reliance on large amounts of data for effective performance have shifted the focus from traditional human-annotated labels to unsupervised learning and pretraining strategies that uncover hidden structures within the data. In response to this challenge, self-supervised learning (SSL) has emerged as a promising paradigm. SSL leverages inherent relationships within the data itself as a form of supervision, eliminating the need for manual labeling and offering a more scalable and resource-efficient alternative for model training. Given these advantages, it is imperative to explore the integration of SSL techniques with ViTs, particularly in scenarios with limited labeled data. Inspired by this evolving trend, this survey aims to systematically review SSL mechanisms tailored for ViTs. We propose a comprehensive taxonomy to classify SSL techniques based on their representations and pre-training tasks. Additionally, we discuss the motivations behind SSL, review prominent pre-training tasks, and highlight advancements and challenges in this field. Furthermore, we conduct a comparative analysis of various SSL methods designed for ViTs, evaluating their strengths, limitations, and applicability to different scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE Workshop on Applications of computer vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

Group shift pointwise convolution for volumetric medical image segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Junjun Ye, Jin Li, Cheng Song, Diping Chen, Wanli Wang, Shanshan Gu, Lixu Qiao, Yu School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Shanghai AI Lab Shanghai China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Chinese University of Hong Kong Hong Kong Peng Cheng Laboratory Guangdong Shenzhen China Pazhou Lab Guangdong Guangzhou China

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models employing 3D convolutions introduce more trainable parameters and are more computationally complex, which may lead easily to model overfitting especially for medical applications with limited available training data. This paper aims to improve the effectiveness and efficiency of 3D convolutions by introducing a novel Group Shift Pointwise Convolution (GSP-Conv). GSP-Conv simplifies 3D convolutions into pointwise ones with 1 × 1 × 1 kernels, which dramatically reduces the number of model parameters and FLOPs (e.g. 27× fewer than 3D convolutions with 3 × 3 × 3 kernels). Naïve pointwise convolutions with limited receptive fields cannot make full use of the spatial image context. To address this problem, we propose a parameter-free operation, Group Shift (GS), which shifts the feature maps along different spatial directions in an elegant way. With GS, pointwise convolutions can access features from different spatial locations, and the limited receptive fields of pointwise convolutions can be compensated. We evaluate the proposed methods on two datasets, PROMISE12 and BraTS18. Results show that our method, with substantially decreased model complexity, achieves comparable or even better performance than models employing 3D convolutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fang, Meiling Huber, Marco Fierrez, Julian Ramachandra, Raghavendra Damer, Naser Alkhaddour, Alhasan Kasantcev, Maksim Pryadchenko, Vasiliy Yang, Ziyuan Huangfu, Huijie Chen, Yingyu Zhang, Yi Pan, Yuchen Jiang, Junjun Liu, Xianming Sun, Xianyun Wang, Caiyong Liu, Xingyu Chang, Zhaohua Zhao, Guangzhe Tapia, Juan Gonzalez-Soler, Lazaro Aravena, Carlos Schulz, Daniel Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norway ID R&D Inc. New York United States School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks. © 2023, CC BY-NC-SA.

关键词： Competition