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
收藏
页数：10
相关论文
共 50 条
  • [1] Learning Sparse Features in Convolutional Neural Networks for Image Classification
    Luo, Wei
    Li, Jun
    Xu, Wei
    Yang, Jian
    INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING: IMAGE AND VIDEO DATA ENGINEERING, ISCIDE 2015, PT I, 2015, 9242 : 29 - 38
  • [2] Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification
    de Lima, Rafael Pires
    Duarte, David
    GEOSCIENCES, 2021, 11 (08)
  • [3] Combining Very Deep Convolutional Neural Networks and Recurrent Neural Networks for Video Classification
    Kiziltepe, Rukiye Savran
    Gan, John Q.
    Escobar, Juan Jose
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2019, PT II, 2019, 11507 : 811 - 822
  • [4] Sparse Pixel Training of Convolutional Neural Networks for Land Cover Classification
    Laban, Noureldin
    Abdellatif, Bassam
    Ebeid, Hala M.
    Shedeed, Howida A.
    Tolba, Mohamed F.
    IEEE ACCESS, 2021, 9 : 52067 - 52078
  • [5] SUnCNN: Sparse Unmixing Using Unsupervised Convolutional Neural Network
    Rasti, Behnood
    Koirala, Bikram
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [6] Multiclass Live Streaming Video Quality Classification Based on Convolutional Neural Networks
    Chen, T.
    Grabs, E.
    Petersons, E.
    Efrosinin, D.
    Ipatovs, A.
    Bogdanovs, N.
    Rjazanovs, D.
    AUTOMATIC CONTROL AND COMPUTER SCIENCES, 2022, 56 (05) : 455 - 466
  • [7] Multiclass Live Streaming Video Quality Classification Based on Convolutional Neural Networks
    T. Chen
    E. Grabs
    E. Petersons
    D. Efrosinin
    A. Ipatovs
    N. Bogdanovs
    D. Rjazanovs
    Automatic Control and Computer Sciences, 2022, 56 : 455 - 466
  • [8] Convolutional Neural Networks Analyzed via Convolutional Sparse Coding
    Papyan, Vardan
    Romano, Yaniv
    Elad, Michael
    JOURNAL OF MACHINE LEARNING RESEARCH, 2017, 18 : 1 - 52
  • [9] Motor imagery classification using sparse nonnegative matrix factorization and convolutional neural networks
    Poonam Chaudhary
    Yash Vardhan Varshney
    Gautam Srivastava
    Surbhi Bhatia
    Neural Computing and Applications, 2024, 36 : 213 - 223
  • [10] Features Extraction for Live Streaming Video Classification with Deep and Convolutional Neural Networks
    Grabs, Elans
    Chen, Tianhua
    Petersons, Ernests
    Efrosinin, Dmitry
    Ipatovs, Aleksandrs
    Kluga, Janis
    Culkovs, Dmitrijs
    2021 IEEE WORKSHOP ON MICROWAVE THEORY AND TECHNIQUES IN WIRELESS COMMUNICATIONS, MTTW'21, 2021, : 58 - 63
12345