Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters
























1,465 Hits in 4.5 sec

CasSeqGCN: Combining Network Structure and Temporal Sequence to Predict Information Cascades [article]

Yansong Wang, Xiaomeng Wang, Radosław Michalski, Yijun Ran, Tao Jia
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.5 MB)
https://web.archive.org/web/20211016231603/https://arxiv.org/pdf/2110.06836v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2110.06836v1 fatcat:l3gacugjybcktnkxo6irnht6rq
CasSeqGCN predicts the future cascade size more accurately compared with other state-of-art baseline methods.  ...  One important task in the study of information cascade is to predict the future recipients of a message given its past spreading trajectory.  ...  CasSeqGCN CN uses the capsule network for aggregation, CasSeqGCN MH uses the multi-head attention mechanism and CasSeqGCN Mean simply average all node vectors to aggregate.  ... 
arXiv:2110.06836v2 fatcat:svtsh5iz3nfydagw5v5eea6moe
Multiple Versions
Citation

Yansong Wang, Xiaomeng Wang, Radosław Michalski, Yijun Ran, Tao Jia. "CasSeqGCN: Combining Network Structure and Temporal Sequence to Predict Information Cascades." arXiv (2022)

IEEE Access Special Section Editorial: Advanced Data Mining Methods for Social Computing

Yongqiang Zhao, Shirui Pan, Jia Wu, Huaiyu Wan, Huizhi Liang, Haishuai Wang, Huawei Shen
2020 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (12.2 MB)
https://web.archive.org/web/20210224053332/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09311472.pdf?tp=&arnumber=9311472&isnumber=8948470&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

The article by Hu, ''Integrating hierarchical attentions for future subevent prediction,'' presents a novel hierarchical attention-based end-to-end model for future subevent prediction using large-scale  ...  In the fifth group, the article ''Modeling and analyzing the influence of multi-information coexistence on attention,'' by Zhao et al., proposes a multiple information coexistence attention model, which  ... 
doi:10.1109/access.2020.3043060 fatcat:qbqk5f4ojvadlazhk2mc343sra
DOAJ
Citation

Yongqiang Zhao, Shirui Pan, Jia Wu, Huaiyu Wan, Huizhi Liang, Haishuai Wang, Huawei Shen. "IEEE Access Special Section Editorial: Advanced Data Mining Methods for Social Computing." IEEE Access (2020) 228598-228604

CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks [article]

Hongjun Zhu, Shun Yuan, Xin Liu, Kuo Chen, Chaolong Jia, Ying Qian
2023 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20231211201701/https://arxiv.org/ftp/arxiv/papers/2308/2308.04961.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL. The file type is application/pdf.

we propose the Cross-Domain Information Fusion Framework (CasCIFF), which is tailored for information cascade prediction.  ...  Existing approaches for information cascade prediction fall into three main categories: feature-driven methods, point process-based methods, and deep learning-based methods.  ...  MuCas [10] : This model uses a multi-scale graph capsule network and an influence attention mechanism to learn the latent representation of cascade graphs.  ... 
arXiv:2308.04961v1 fatcat:jz5akzp5bzb53dtehiiikkky3u
Open Access
Citation

Hongjun Zhu, Shun Yuan, Xin Liu, Kuo Chen, Chaolong Jia, Ying Qian. "CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks." arXiv (2023)

MR-CapsNet: A Deep Learning Algorithm for Image-Based Head Pose Estimation on CapsNet

Hao Fang, Jun-Qing Liu, Kai Xie, Peng Wu, Xin-Yu Zhang, Chang Wen, Jian-Biao He
2021 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.3 MB)
https://web.archive.org/web/20211019112915/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09568882.pdf?tp=&arnumber=9568882&isnumber=6514899&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

In this report, we propose a Multi stage Regression-Capsule Network (MR-CapsNet) to predict head posture based on a single image input.  ...  INDEX TERMS Head pose estimation, Multi-stage Regression, Squeeze-and-excitation Block, Capsule Network  ...  Therefore, we combined the extracted feature map with CapsNet to obtain more accurate attitude information. Finally, a multi-stage regression function was used to predict head posture.  ... 
doi:10.1109/access.2021.3119615 fatcat:p6cuxdwdnzhvvgfpsjuithksna
DOAJ
Citation

Hao Fang, Jun-Qing Liu, Kai Xie, Peng Wu, Xin-Yu Zhang, Chang Wen, Jian-Biao He. "MR-CapsNet: A Deep Learning Algorithm for Image-Based Head Pose Estimation on CapsNet." IEEE Access (2021) 1-1

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis [article]

Ben Fei, Weidong Yang, Wenming Chen, Zhijun Li, Yikang Li, Tao Ma, Xing Hu, Lipeng Ma
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.6 MB)
https://web.archive.org/web/20220314013636/https://arxiv.org/pdf/2203.03311v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2022 pre-print
arXiv:2203.03311v1 fatcat:pekfmqvgvbdlzhvh4upj6m2kce
2022 accepted
arXiv:2203.03311v3 fatcat:qhlkoqfs7bdwhi54d74yomskha
Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc.  ...  a multi-scale graph, greatly enhancing the coding features.  ...  After the graph is built, all the regional features are gathered, and the graph is convolved with multi-head attention.  ... 
arXiv:2203.03311v2 fatcat:e2kvryolufearetp4ujlw2gwwy
Multiple Versions
Citation

Ben Fei, Weidong Yang, Wenming Chen, Zhijun Li, Yikang Li, Tao Ma, Xing Hu, Lipeng Ma. "Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis." arXiv (2022)

H2CGL: Modeling Dynamics of Citation Network for Impact Prediction [article]

Guoxiu He, Zhikai Xue, Zhuoren Jiang, Yangyang Kang, Star Zhao, Wei Lu
2023 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.0 MB)
https://web.archive.org/web/20231018082303/https://arxiv.org/pdf/2305.01572v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL. The file type is application/pdf.

Other Versions

2023 pre-print
arXiv:2305.01572v1 fatcat:sblus3vtxjg7njijmsjml3dbtu
2023 pre-print
arXiv:2305.01572v2 fatcat:bih7srywinanti5afhywbmdceu
In this study, we construct hierarchical and heterogeneous graphs for target papers with an annual perspective.  ...  The constructed graphs can record the annual dynamics of target papers' scientific context information.  ...  72234005), the Shanghai Planning Office of Philosophy and Social Science Youth Project (2022ETQ001), the Natural Science Foundation of Zhejiang Province (LY22G030002), the Fundamental Research Funds for  ... 
arXiv:2305.01572v3 fatcat:25c7z2g5p5ebdk2wii3uequ4um
Open Access Multiple Versions
Citation

Guoxiu He, Zhikai Xue, Zhuoren Jiang, Yangyang Kang, Star Zhao, Wei Lu. "H2CGL: Modeling Dynamics of Citation Network for Impact Prediction." arXiv (2023)

Deep Learning for Micro-expression Recognition: A Survey [article]

Yante Li, Jinsheng Wei, Yang Liu, Janne Kauttonen, Guoying Zhao
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.4 MB)
https://web.archive.org/web/20221011074225/https://arxiv.org/pdf/2107.02823v5.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2107.02823v1 fatcat:rkgr4tm5avfr3nhbexua4kk57e
2021 pre-print
arXiv:2107.02823v2 fatcat:xfe4pghk55e4nnecyv6ll7ugcm
2021 pre-print
arXiv:2107.02823v3 fatcat:43gbbsvfjfa3bpw5zttuvo63tm
2021 pre-print
arXiv:2107.02823v4 fatcat:w2bqbvxw4zbc7jjnqmx2gmh5aa
Recently, with the success of deep learning (DL) in various fields, neural networks have received increasing interests in MER.  ...  Different from macro-expressions, MEs are spontaneous, subtle, and rapid facial movements, leading to difficult data collection, thus have small-scale datasets.  ...  ACKNOWLEDGEMENT This work was supported by the Academy of Finland for Academy Professor project EmotionAI (grants 336116, 345122), by Ministry of Education and Culture of Finland for AI forum project and  ... 
arXiv:2107.02823v5 fatcat:gfdriwzvkbb57asb6g2wpwfoiu
Open Access Multiple Versions
Citation

Yante Li, Jinsheng Wei, Yang Liu, Janne Kauttonen, Guoying Zhao. "Deep Learning for Micro-expression Recognition: A Survey." arXiv (2022)

E2-Capsule Neural Networks for Facial Expression Recognition Using AU-Aware

Shan Cao, Yuqian Yao, Gaoyun An
2020 IET Image Processing  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.5 MB)
https://web.archive.org/web/20210715030058/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/iet-ipr.2020.0063

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

In this study, one double enhanced capsule neural network (E2-Capsnet) that uses AU-aware attention for facial expression recognition (FER) is proposed.  ...  The first enhancement module is the convolutional neural network with AU-aware attention, which can focus on the active areas of the expression.  ...  In future work, we consider applying the graph convolutional network with the capsule network to take advantage of the structural information of the graph, which can deal with more complex facial expression  ... 
doi:10.1049/iet-ipr.2020.0063 fatcat:xjjycm6yuvbxpndndzceiz55ne
DOAJ
Citation

Shan Cao, Yuqian Yao, Gaoyun An. "E2-Capsule Neural Networks for Facial Expression Recognition Using AU-Aware." IET Image Processing 14.11 (2020)

"Reading Pictures Instead of Looking": RGB-D Image-Based Action Recognition via Capsule Network and Kalman Filter

Botong Zhao, Yanjie Wang, Keke Su, Hong Ren, Haichao Sun
2021 Sensors  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.1 MB)
https://web.archive.org/web/20210404033057/https://res.mdpi.com/d_attachment/sensors/sensors-21-02217/article_deploy/sensors-21-02217.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

A Kalman filter analyzes the predicted capsules and filters out any misinformation to prevent the action recognition results from being affected by incorrectly predicted capsules.  ...  With a 90% observation rate, the OAD dataset test precision is 83.3%, the ChaLearn Gesture dataset test precision is 72.2%, and the G3D dataset test precision is 86.5%.  ...  Informed Consent Statement: Informed consent was obtained from all subjects involved in the study. Data Availability Statement: The data in Tables 1-5 is availability.  ... 
doi:10.3390/s21062217 pmid:33810140 pmcid:PMC8005215 fatcat:ye63sqrppbap5izz3wi6zb3t6e
DOAJ
Citation

Botong Zhao, Yanjie Wang, Keke Su, Hong Ren, Haichao Sun. ""Reading Pictures Instead of Looking": RGB-D Image-Based Action Recognition via Capsule Network and Kalman Filter." Sensors 21.6 (2021)

MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network

Ankit Pal, Muru Selvakumar, Malaikannan Sankarasubbu
2020 Proceedings of the 12th International Conference on Agents and Artificial Intelligence  

Preserved Fulltext

Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20200328015910/https://arxiv.org/pdf/2003.11644v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2020 pre-print arXiv:2003.11644v1 fatcat:spj6osa4fjhtbejvvgqvp5syaq
The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task.  ...  In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels.  ...  Graph Attention Networks for multi-label classification In GCNs, the neighborhoods of nodes combine with equal or pre-defined weights.  ... 
doi:10.5220/0008940304940505 dblp:conf/icaart/PalSS20 fatcat:yxfhnixwdfbphcuzxc46cijz5e
Multiple Versions
Citation

Ankit Pal, Muru Selvakumar, Malaikannan Sankarasubbu. "MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network." Proceedings of the 12th International Conference on Agents and Artificial Intelligence (2020) 494-505

IEEE Access Special Section Editorial: AI-Driven Big Data Processing: Theory, Methodology, and Applications

Zhanyu Ma, Sunwoo Kim, Pascual Martinez-Gomez, Jalil Taghia, Yi-Zhe Song, Huiji Gao
2020 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20201111151408/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09254098.pdf?tp=&arnumber=9254098&isnumber=8948470&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

The article by Zhang et al., ''Multi-task cascaded convolutional networks based intelligent fruit detection for designing automated robot,'' proposes an improved multi-task cascaded convolutional network-based  ...  network platforms and combines the textual information with sentiment time series to achieve multi-document sentiment prediction.  ...  The authors present a multi-scale adjacent connection module (ACM) to provide effective contextual information and reduce interference for vehicle detection.  ... 
doi:10.1109/access.2020.3035461 fatcat:rt7ejtponrfexigie4cfpt7gd4
DOAJ
Citation

Zhanyu Ma, Sunwoo Kim, Pascual Martinez-Gomez, Jalil Taghia, Yi-Zhe Song, Huiji Gao. "IEEE Access Special Section Editorial: AI-Driven Big Data Processing: Theory, Methodology, and Applications." IEEE Access (2020) 199882-199898

Human Behavior Analysis: A Survey on Action Recognition

Bruno Degardin, Hugo Proença
2021 Applied Sciences  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (25.1 MB)
https://web.archive.org/web/20210908113818/https://mdpi-res.com/d_attachment/applsci/applsci-11-08324/article_deploy/applsci-11-08324.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison  ...  , the lower-level capsules will make predictions for smaller regions of the image, with the rationale that when multiple low-level capsules achieve a prediction consensus, a higher-level capsule will become  ...  Following a masking procedure, the capsule activations are set to 0, except for the capsule representing the ground truth class, predicting the action localisation through the largest activation and feeding  ... 
doi:10.3390/app11188324 fatcat:zenvfhlaubht7ar3qrpil4lgdm
DOAJ
Citation

Bruno Degardin, Hugo Proença. "Human Behavior Analysis: A Survey on Action Recognition." Applied Sciences 11.18 (2021) 8324

A Survey on Text Classification: From Shallow to Deep Learning [article]

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, Lifang He
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.5 MB)
https://web.archive.org/web/20220103222904/https://arxiv.org/pdf/2008.00364v6.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2008.00364v5 fatcat:d3b2ifxy4jgdhn2cwqz7bpsdlu
2020 pre-print
arXiv:2008.00364v4 fatcat:slw7rt4kc5cjxdglm2w3doydqu
2020 pre-print
arXiv:2008.00364v3 fatcat:zfvota353jgm3p3dt3gat6gkia
2020 pre-print
arXiv:2008.00364v2 fatcat:fpk4o2kcjjhchkgklq3afmi5ny
2020 pre-print
arXiv:2008.00364v1 fatcat:oxrrwle5sbgcjksuqjxoituqzm
We then discuss each of these categories in detail, dealing with both the technical developments and benchmark datasets that support tests of predictions.  ...  We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification.  ...  Thanks for computing infrastructure provided by Huawei MindSpore platform.  ... 
arXiv:2008.00364v6 fatcat:a6zp52rtf5awlh253yp62wqt3a
Multiple Versions
Citation

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, Lifang He. "A Survey on Text Classification: From Shallow to Deep Learning." arXiv (2021)

A Survey on Text Classification: From Traditional to Deep Learning

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, Lifang He
2022 ACM Transactions on Intelligent Systems and Technology  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20220608123520/https://dl.acm.org/doi/pdf/10.1145/3495162

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

We then discuss each of these categories in detail, dealing with both the technical developments and benchmark datasets that support tests of predictions.  ...  We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification.  ...  ACKNOWLEDGMENTS Thanks for computing infrastructure provided by Huawei MindSpore platform.  ... 
doi:10.1145/3495162 fatcat:ehrzpu4eezf7lah6jm3gyksyaq
Citation

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, Lifang He. "A Survey on Text Classification: From Traditional to Deep Learning." ACM Transactions on Intelligent Systems and Technology 13.2 (2022) 1-41

Medical Image Segmentation Using Deep Learning: A Survey [article]

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.2 MB)
https://web.archive.org/web/20220105224917/https://arxiv.org/pdf/2009.13120v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2009.13120v2 fatcat:2hktufsbxnhsvlll3m6fxdgjne
2020 pre-print
arXiv:2009.13120v1 fatcat:dunemkyjdzcrjecxztpgfgm5zu
currently popular literatures according to a multi-level structure from coarse to fine.  ...  Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field.  ...  attention usually exhibit better performance than normal CNNs for image segmentation tasks. 5) Multi-scale Information Fusion: One of the challenges in medical image segmentation is a large range of scales  ... 
arXiv:2009.13120v3 fatcat:ntgbqwkz55axrjum72elbm6rry
Multiple Versions
Citation

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi. "Medical Image Segmentation Using Deep Learning: A Survey." arXiv (2021)

« Previous Showing results 1 — 15 out of 1,465 results