Group k-Sparse Temporal Convolutional Neural Networks: Unsupervised Pretraining for Video Classification

被引：1

作者：

Milacski, Zoltan A. ^{[1
]}

Poczos, Barnabas ^{[2
]}

Lorincz, Andras ^{[1
]}

机构：

[1] Eotvos Lorand Univ, Fac Informat, Budapest, Hungary

[2] Carnegie Mellon Univ, Machine Learning Dept, Pittsburgh, PA 15213 USA

来源：

2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2019年

关键词：

group sparsity; temporal; convolutional neural networks; unsupervised learning; video data;

D O I：

10.1109/ijcnn.2019.8852057

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we propose Group k-Sparse Temporal Convolutional Neural Networks for unsupervised pretraining using video data. Our work is the first to consider the recurrent extension of structured sparsity, thus enhancing representational power and explainability. We show that our architecture is able to outperform several state-of-the-art baselines on Rotated MNIST, Scanned CIFAR-10, COIL-100 and NEC Animal pretraining benchmarks for video classification using limited labeled data.

引用

页数：10

共 50 条

[21] Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images
Huang, Yue
Zheng, Han
Liu, Chi
Ding, Xinghao
Rohde, Gustavo K.
[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2017, 21 (06) : 1625 - 1632
[22] Investigation of the Efficiency of Unsupervised Learning for Multi-task Classification in Convolutional Neural Network
Kim, Jonghong
Jang, Gil-Jin
Lee, Minho
[J]. NEURAL INFORMATION PROCESSING, ICONIP 2016, PT III, 2016, 9949 : 547 - 554
[23] Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
Dosovitskiy, Alexey
Fischer, Philipp
Springenberg, Jost Tobias
Riedmiller, Martin
Brox, Thomas
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (09) : 1734 - 1747
[24] Unsupervised Network Intrusion Detection Using Convolutional Neural Networks
Alam, Shumon
Alam, Yasin
Cui, Suxia
Akujuobi, Cajetan M.
[J]. 2023 IEEE 13TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE, CCWC, 2023, : 712 - 717
[25] Age group classification to identify the progress of language development based on convolutional neural networks
Oh, Byoung-Doo
Lee, Yoon-Kyoung
Song, Hye-Jeong
Kim, Jong-Dae
Park, Chan-Young
Kim, Yu-Seop
[J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2021, 40 (04) : 7745 - 7754
[26] Ship classification based on convolutional neural networks
Li Zhenzhen
Zhao Baojun
Tang Linbo
Li Zhen
Feng Fan
[J]. JOURNAL OF ENGINEERING-JOE, 2019, 2019 (21): : 7343 - 7346
[27] Classification of Radar Signals with Convolutional Neural Networks
Hong, Seok-Jun
Yi, Yearn-Gui
Jo, Jeil
Seo, Bo-Seok
[J]. 2018 TENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2018), 2018, : 894 - 896
[28] Plant Classification using Convolutional Neural Networks
Yalcin, Hulya
Razavi, Salar
[J]. 2016 FIFTH INTERNATIONAL CONFERENCE ON AGRO-GEOINFORMATICS (AGRO-GEOINFORMATICS), 2016, : 233 - 237
[29] Sound Classification Using Convolutional Neural Networks
Jaiswal, Kaustumbh
Patel, Dhairya Kalpeshbhai
[J]. 2018 SEVENTH IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING IN EMERGING MARKETS (CCEM), 2018, : 81 - 84
[30] Convolutional Neural Networks for Web Documents Classification
Artene, Codrut-Georgian
Tibeica, Marius Nicolae
Vecliuc, Dumitru Daniel
Leon, Florin
[J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2021, 2021, 12672 : 289 - 302

← 1 2 3 4 5 →