Corpus ID: 18321045

Towards Good Practices for Very Deep Two-Stream ConvNets

  title={Towards Good Practices for Very Deep Two-Stream ConvNets},
  author={L. Wang and Yuanjun Xiong and Zhe Wang and Yu Qiao},
  • L. Wang, Yuanjun Xiong, +1 author Yu Qiao
  • Published 2015
  • Computer Science
  • ArXiv
  • Deep convolutional networks have achieved great success for object recognition in still images. However, for action recognition in videos, the improvement of deep convolutional networks is not so evident. We argue that there are two reasons that could probably explain this result. First the current network architectures (e.g. Two-stream ConvNets) are relatively shallow compared with those very deep models in image domain (e.g. VGGNet, GoogLeNet), and therefore their modeling capacity is… CONTINUE READING
    302 Citations
    Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
    • 1
    • Highly Influenced
    Fully convolutional networks for action recognition
    • 17
    Pooling the Convolutional Layers in Deep ConvNets for Video Action Recognition
    • 74
    • PDF
    Two-Stream Designed 2D/3D Residual Networks with Lstms for Action Recognition in Videos
    • 1
    Simple, Efficient and Effective Encodings of Local Deep Features for Video Action Recognition
    • 4
    • Highly Influenced
    • PDF
    Video Action Recognition Based on Deeper Convolution Networks with Pair-Wise Frame Motion Concatenation
    • 6
    • PDF
    Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition
    • 12
    Convolutional Two-Stream Network Fusion for Video Action Recognition
    • 1,400
    • PDF
    Deep Learning for Action and Gesture Recognition in Image Sequences: A Survey
    • 29
    • Highly Influenced
    • PDF


    Two-Stream Convolutional Networks for Action Recognition in Videos
    • 4,088
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 41,218
    • Highly Influential
    • PDF
    Beyond short snippets: Deep networks for video classification
    • 1,561
    • PDF
    Large-Scale Video Classification with Convolutional Neural Networks
    • 4,174
    • PDF
    Going deeper with convolutions
    • 20,841
    • PDF
    Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice
    • 517
    • PDF
    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
    • 8,392
    • PDF
    Action recognition with trajectory-pooled deep-convolutional descriptors
    • L. Wang, Yu Qiao, X. Tang
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    • 863
    • PDF