scholarly journals Maritime vessel re-identification: novel VR-VCA dataset and a multi-branch architecture MVR-net

2021 ◽  
Vol 32 (3) ◽  
Author(s):  
Amir Ghahremani ◽  
Tunc Alkanat ◽  
Egor Bondarev ◽  
Peter H. N. de With
Keyword(s):  
Deep Learning ◽  
Best Practices ◽  
Large Scale ◽  
Flow Analysis ◽  
Challenging Problem ◽  
Maritime Traffic ◽  
Large Scale Dataset ◽  
Identity Matching ◽  
Learning Architectures ◽  
Disjoint Camera Views

AbstractMaritime vessel re-identification (re-ID) is a computer vision task of vessel identity matching across disjoint camera views. Prominent applications of vessel re-ID exist in the fields of surveillance and maritime traffic flow analysis. However, the field suffers from the absence of a large-scale dataset that enables training of deep learning models. In this study, we present a new dataset that includes 4614 images of 729 vessels along with 5-bin orientation and 8-class vessel-type annotations to promote further research. A second contribution of this study is the baseline re-ID analysis of our new dataset. Performances of 10 recent deep learning architectures are quantitatively compared to reveal the best practices. Lastly, we propose a novel multi-branch deep learning architecture, Maritime Vessel Re-ID network (MVR-net), to address the challenging problem of vessel re-ID. Evaluation of our approach on the new dataset yields 74.5% mAP and 77.9% Rank-1 score, providing a performance increase of 5.7% mAP and 5.0% Rank-1 over the best-performing baseline. MVR-net also outperforms the PRN (a pioneering vehicle re-ID network), by 2.9% and 4.3% higher mAP and Rank-1, respectively.

scholarly journals A Large-Scale Evaluation Framework for EEG Deep Learning Architectures

2018 ◽  
Author(s):  
Felix A. Heilmeyer ◽  
Robin T. Schirrmeister ◽  
Lukas D. J. Fiederer ◽  
Martin Volker ◽  
Joos Behncke ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Evaluation Framework ◽  
Scale Evaluation ◽  
Learning Architectures

scholarly journals Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study

2021 ◽  
Vol 178 ◽  
pp. 171-186
Author(s):  
Gabriel Henrique de Almeida Pereira ◽  
Andre Minoro Fusioka ◽  
Bogdan Tomoyuki Nassu ◽  
Rodrigo Minetto
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Fire Detection ◽  
Landsat 8 ◽  
Learning Study ◽  
Active Fire ◽  
Large Scale Dataset

scholarly journals A question-entailment approach to question answering

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Asma Ben Abacha ◽  
Dina Demner-Fushman
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Question Answering ◽  
Evaluation Process ◽  
Substantial Improvement ◽  
Challenging Problem ◽  
Fine Grained ◽  
Domain Specific ◽  
Answer Extraction ◽  
Medical Task

Abstract Background One of the challenges in large-scale information retrieval (IR) is developing fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging problem due to the difficulty of the question understanding and answer extraction tasks. One of the promising tracks investigated in QA is mapping new questions to formerly answered questions that are “similar”. Results We propose a novel QA approach based on Recognizing Question Entailment (RQE) and we describe the QA system and resources that we built and evaluated on real medical questions. First, we compare logistic regression and deep learning methods for RQE using different kinds of datasets including textual inference, question similarity, and entailment in both the open and clinical domains. Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers. To study the end-to-end QA approach, we built the MedQuAD collection of 47,457 question-answer pairs from trusted medical sources which we introduce and share in the scope of this paper. Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score. Conclusions The evaluation results support the relevance of question entailment for QA and highlight the effectiveness of combining IR and RQE for future QA efforts. Our findings also show that relying on a restricted set of reliable answer sources can bring a substantial improvement in medical QA.

scholarly journals A Deep Learning Sentiment Analyser for Social Media Comments in Low-Resource Languages

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1133
Author(s):  
Zenun Kastrati ◽  
Lule Ahmedi ◽  
Arianit Kurti ◽  
Fatbardh Kadriu ◽  
Doruntina Murtezaj ◽  
...  
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Large Scale ◽  
Research Study ◽  
Low Resource ◽  
Analysis Task ◽  
Large Scale Dataset ◽  
Social Media Platforms ◽  
Experimental Findings

During the pandemic, when people needed to physically distance, social media platforms have been one of the outlets where people expressed their opinions, thoughts, sentiments, and emotions regarding the pandemic situation. The core object of this research study is the sentiment analysis of peoples’ opinions expressed on Facebook regarding the current pandemic situation in low-resource languages. To do this, we have created a large-scale dataset comprising of 10,742 manually classified comments in the Albanian language. Furthermore, in this paper we report our efforts on the design and development of a sentiment analyser that relies on deep learning. As a result, we report the experimental findings obtained from our proposed sentiment analyser using various classifier models with static and contextualized word embeddings, that is, fastText and BERT, trained and validated on our collected and curated dataset. Specifically, the findings reveal that combining the BiLSTM with an attention mechanism achieved the highest performance on our sentiment analysis task, with an F1 score of 72.09%.

scholarly journals Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography

2019 ◽  
Vol 38 (9) ◽  
pp. 2198-2210 ◽  
Author(s):  
Sarah Leclerc ◽  
Erik Smistad ◽  
Joao Pedrosa ◽  
Andreas Ostvik ◽  
Frederic Cervenansky ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
2D Echocardiography ◽  
Large Scale Dataset

scholarly journals A New Deep Learning-Based Zero-Inflated Duration Model for Financial Data Irregularly Spaced in Time

2021 ◽  
Vol 9 ◽  
Author(s):  
Yong Shi ◽  
Wei Dai ◽  
Wen Long
Keyword(s):  
Deep Learning ◽  
Hybrid Model ◽  
Large Scale ◽  
Stock Exchange ◽  
Small Individual ◽  
Arrival Times ◽  
Large Scale Dataset ◽  
Duration Distribution ◽  
Zero Values ◽  
Individual Traders

In stock trading markets, trade duration (i. e., inter-arrival times of trades) usually exhibits high uncertainty and excessive zero values. To forecast conditional distribution of trade duration, this study proposes a hybrid model called “DL-ZIACD” for short, which addresses the problem of excessive zero values by a zero-inflated distribution. Meanwhile, dynamics of the distribution time-varying parameters are captured by a specially designed deep learning (DL) architecture in which the behavioral patterns of large traders and small individual traders are represented separately by different blocks. The proposed hybrid model takes advantage of the strong fitting ability of deep learning methods while allowing for providing a probabilistic output. This paper empirically applied the established model to a large-scale dataset, containing 9,900,000 transactions of the Chinese Shenzhen Stock Exchange 100 Index (SZSE 100) constituents. To the best of our knowledge, no previous studies have applied conditional duration models to a dataset of such a large scale. For both the central location forecasting and the extreme quantile forecasting, our proposed model exhibited significant superiority over the benchmark models, which indicates that our DL-ZIACD model can provide accurate forecasts in conditional duration distribution.

scholarly journals AI-Powered Oracle Bone Inscriptions Recognition and Fragments Rejoining

2020 ◽  
Author(s):  
Chongsheng Zhang ◽  
Ruixing Zong ◽  
Shuang Cao ◽  
Yi Men ◽  
Bofeng Mo
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Template Matching ◽  
Large Scale ◽  
Matching Algorithm ◽  
Domain Experts ◽  
Detection Algorithms ◽  
Scene Text Detection ◽  
Large Scale Dataset ◽  
Scene Text

Oracle Bone Inscriptions (OBI) research is very meaningful for both history and literature. In this paper, we introduce our contributions in AI-Powered Oracle Bone (OB) fragments rejoining and OBI recognition. (1) We build a real-world dataset OB-Rejoin, and propose an effective OB rejoining algorithm which yields a top-10 accuracy of 98.39%. (2) We design a practical annotation software to facilitate OBI annotation, and build OracleBone-8000, a large-scale dataset with character-level annotations. We adopt deep learning based scene text detection algorithms for OBI localization, which yield an F-score of 89.7%. We propose a novel deep template matching algorithm for OBI recognition which achieves an overall accuracy of 80.9%. Since we have been cooperating closely with OBI domain experts, our effort above helps advance their research. The resources of this work are available at https://github.com/chongshengzhang/OracleBone.

Soil/Tire Interaction Analysis Using FEM and FVM

2005 ◽  
Vol 33 (1) ◽  
pp. 38-62 ◽  
Author(s):  
S. Oida ◽  
E. Seta ◽  
H. Heguri ◽  
K. Kato
Keyword(s):  
Large Scale ◽  
Interaction Analysis ◽  
Yield Criterion ◽  
Surrounding Medium ◽  
Flow Analysis ◽  
Measurement Data ◽  
Traction Force ◽  
Elastoplastic Material ◽  
The Road ◽  
Soil Flow

Abstract Vehicles, such as an agricultural tractor, construction vehicle, mobile machinery, and 4-wheel drive vehicle, are often operated on unpaved ground. In many cases, the ground is deformable; therefore, the deformation should be taken into consideration in order to assess the off-the-road performance of a tire. Recent progress in computational mechanics enabled us to simulate the large scale coupling problem, in which the deformation of tire structure and of surrounding medium can be interactively considered. Using this technology, hydroplaning phenomena and tire traction on snow have been predicted. In this paper, the simulation methodology of tire/soil coupling problems is developed for pneumatic tires of arbitrary tread patterns. The Finite Element Method (FEM) and the Finite Volume Method (FVM) are used for structural and for soil-flow analysis, respectively. The soil is modeled as an elastoplastic material with a specified yield criterion and a nonlinear elasticity. The material constants are referred to measurement data, so that the cone penetration resistance and the shear resistance are represented. Finally, the traction force of the tire in a cultivated field is predicted, and a good correlation with experiments is obtained.

Sign in / Sign up

Export Citation Format

Share Document