Filters








19,618 Hits in 5.2 sec

Preface

Min-Ling Zhang, Sheng-Jun Huang, Ming-Sheng Long
2021 Journal of Computer Science and Technology  
The authors propose a deep cascade framework to incorporate multi-scale signal coding with deep cascade coding.  ...  These contributions show advanced technologies on learning from small samples, including disambiguation-based partial label learning, source-free domain adaptation, and deep cascade models.  ...  The authors propose a deep cascade framework to incorporate multi-scale signal coding with deep cascade coding.  ... 
doi:10.1007/s11390-021-0004-1 fatcat:fvcyxvkw2reohg7t2feotxonfe

Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant [article]

Yu Gong, Xusheng Luo, Yu Zhu, Wenwu Ou, Zhao Li, Muhua Zhu, Kenny Q. Zhu, Lu Duan, Xi Chen
2019 arXiv   pre-print
In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity  ...  While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions.  ...  We proposed a deep multi-task sequence learning framework with cascade and residual connection.  ... 
arXiv:1803.11326v4 fatcat:ivmfc6lo4nbzzcwlf6biedhmje

Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant

Yu Gong, Xusheng Luo, Yu Zhu, Wenwu Ou, Zhao Li, Muhua Zhu, Kenny Q. Zhu, Lu Duan, Xi Chen
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity  ...  While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions.  ...  We proposed a deep multi-task sequence learning framework with cascade and residual connection.  ... 
doi:10.1609/aaai.v33i01.33016465 fatcat:a5hmxyguu5ht5ghkhgjr36oj5u

A Deep Cascade Model for Multi-Document Reading Comprehension [article]

Ming Yan, Jiangnan Xia, Chen Wu, Bin Bi, Zhongzhou Zhao, Ji Zhang, Luo Si, Rui Wang, Wei Wang, Haiqing Chen
2018 arXiv   pre-print
To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction  ...  Given the complexity of the real-world multi-document MRC scenario, it is difficult to jointly optimize both in an end-to-end system.  ...  multi-task deep MRC model on the remaining content.  ... 
arXiv:1811.11374v1 fatcat:3jtulmdoyjfd3ltxjrnyoy7liu

A Deep Cascade Model for Multi-Document Reading Comprehension

Ming Yan, Jiangnan Xia, Chen Wu, Bin Bi, Zhongzhou Zhao, Ji Zhang, Luo Si, Rui Wang, Wei Wang, Haiqing Chen
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the documentlevel and paragraph-level ranking of candidate texts to more precise answer extraction  ...  Given the complexity of the real-world multi-document MRC scenario, it is difficult to jointly optimize both in an end-to-end system.  ...  multi-task deep MRC model on the remaining content.  ... 
doi:10.1609/aaai.v33i01.33017354 fatcat:lo52vbvoaffjrbbcqloic2kxny

Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network [article]

Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
2018 arXiv   pre-print
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks.  ...  We also present variant models of the proposed cascading residual network to further improve efficiency.  ...  Deep Learning Based Image Super-Resolution Recently, deep learning based models have shown dramatic improvements in the SISR task. Dong et al.  ... 
arXiv:1803.08664v5 fatcat:mflcl63ueng43huqzc46j26v7u

GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation [article]

Taehyeong Kim, Min-Oh Heo, Seonil Son, Kyoung-Wha Park, Byoung-Tak Zhang
2019 arXiv   pre-print
Here we propose a deep learning network model, GLAC Net, that generates visual stories by combining global-local (glocal) attention and context cascading mechanisms.  ...  The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images.  ...  Here we propose a deep learning network model that generates visual stories by combining globallocal (glocal) attention and context cascading mechanisms.  ... 
arXiv:1805.10973v3 fatcat:prg2t6q6y5c7noshoct4fsqigy

Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network [chapter]

Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
2018 Lecture Notes in Computer Science  
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks.  ...  We also present variant models of the proposed cascading residual network to further improve efficiency.  ...  Deep Learning Based Image Super-Resolution Recently, deep learning based models have shown dramatic improvements in the SISR task. Dong et al.  ... 
doi:10.1007/978-3-030-01249-6_16 fatcat:4ibhd6um5jahji3czpqsss2apy

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Learning in Limited Angle Tomography 554 Normative Modeling of Neuroimaging Data using Scalable Multi-Task Gaussian Processes 556 Deep Multi-Structural Shape Analysis: Application to Neuroanatomy 557  ...  via Coarse to Fine Context Memory 295 Deep Learning from Label Proportions for Emphysema Quantification 296 Semi-Automatic RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networks 306 A  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Improved Deep Forest Mode for Detection of Fraudulent Online Transaction

Mian Huang, Lizhi Wang, Zhaohui Zhang
2020 Computing and informatics  
In addition, the autoencoder model is introduced into the detection model to enhance the representation learning ability.  ...  compared to the random forest model, and a beyond 5 % improvement compared to the original deep forest model.  ...  Deep forest (multi-Grained Cascade Forest, gcForest) is a novel decision tree ensemble method, which may open the door towards an alternative to deep neural networks for many tasks [11] .  ... 
doi:10.31577/cai_2020_5_1082 fatcat:4udkvbwobvc75mrnxioi3ztaku

Image Super-Resolution via Progressive Cascading Residual Network

Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we address this issue by adapting a progressive learning scheme to the deep convolutional neural network.  ...  The problem of enhancing the resolution of a single lowresolution image has been popularly addressed by recent deep learning techniques.  ...  With the advancement of deep learning technologies in various computer vision tasks [10, 22, 20] , many deep learning-based models have been proposed to tackle the SISR task [7, 13, 26, 19] .  ... 
doi:10.1109/cvprw.2018.00123 dblp:conf/cvpr/AhnKS18 fatcat:meh2kbmzpvhw5d7aeqzdah7uqy

Learning from Weak-Label Data: A Deep Forest Expedition

Qian-Wei Wang, Liang Yang, Yu-Feng Li
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose LCForest, which is the first tree ensemble based deep learning method for weak-label learning.  ...  Rather than formulating the problem as a regularized framework, we employ the recently proposed cascade forest structure, which processes information layer-by-layer, and endow it with the ability of exploiting  ...  The MLDF method ) makes a first step on adapting deep forest to multi-label learning tasks by designing a multi-layer structure to learn correlations among labels.  ... 
doi:10.1609/aaai.v34i04.6092 fatcat:42v6zgorajah3lalil7l23b2ci

SipBit: A Sensing Platform to Recognize Beverage Type, Volume, and Sugar Content Using Electrical Impedance Spectroscopy and Deep Learning

Chamath Amarasinghe, Nimesha Ranasinghe
2022 CHI Conference on Human Factors in Computing Systems Extended Abstracts  
Then, a multi-task network cascade algorithm was employed to identify eight diferent beverage types in various volume levels and sugar concentrations.  ...  SipBit consists of an electrical impedance measurement unit and a recognition method based on deep learning techniques.  ...  Deep learning models (Multi-task network cascade).  ... 
doi:10.1145/3491101.3519713 fatcat:3t3ccf2dnbem3dkr57ez2uvxbu

A Big Data Analysis Framework Using Apache Spark and Deep Learning [article]

Anand Gupta, Hardeo Thakur, Ritvik Shrivastava, Pulkit Kumar, Sreyashi Nag
2017 arXiv   pre-print
using the popular concept of Cascade Learning.  ...  In this paper, we propose a novel framework that combines the distributive computational abilities of Apache Spark and the advanced machine learning architecture of a deep multi-layer perceptron (MLP),  ...  Work Related to Cascade Learning The two stages of the framework mentioned in this paper, namely analysis using Spark and multi-layer perceptron, is connected via cascading.  ... 
arXiv:1711.09279v1 fatcat:pyhyhv4pcfbzziopnluedigeae

An Automatic Recognition of Tooth-Marked Tongue Based on Tongue Region Detection and Tongue Landmark Detection via Deep Learning

Wenjun Tang, Yuan Gao, Lei Liu, Tingwei Xia, Li He, Song Zhang, Jinhong Guo, Weihong Li, Qiang Xu
2020 IEEE Access  
To address this challenging task, a two-stage method based on tongue region detection and tongue landmark detection via deep learning is proposed in this paper.  ...  Moreover, to the best of our knowledge, we are the first attempt to manage the tooth-marked tongue recognition via deep learning. We conducted extensive experiments with the proposed method.  ...  Inspired by the idea of Multi-task Cascaded Convolutional Networks (MTCNN) [15] , we design a cascaded CNNs with multi-task learning to manage these two tasks simultaneously.  ... 
doi:10.1109/access.2020.3017725 fatcat:6ou6wdmxrnfafghiazm7dnfewe
« Previous Showing results 1 — 15 out of 19,618 results