Corpus ID: 9169990

Two-Stream Convolutional Networks for Dynamic Saliency Prediction

@article{Bak2016TwoStreamCN,
  title={Two-Stream Convolutional Networks for Dynamic Saliency Prediction},
  author={Çagdas Bak and Aykut Erdem and Erkut Erdem},
  journal={ArXiv},
  year={2016},
  volume={abs/1607.04730}
}
  • Çagdas Bak, Aykut Erdem, Erkut Erdem
  • Published 2016
  • Computer Science
  • ArXiv
  • In recent years, visual saliency estimation in images has attracted much attention in the computer vision community. However, predicting saliency in videos has received rela- tively little attention. Inspired by the recent success of deep convolutional neural networks based static saliency mod- els, in this work, we study two different two-stream convo- lutional networks for dynamic saliency prediction. To im- prove the generalization capability of our models, we also introduce a novel… CONTINUE READING
    21 Citations
    Revisiting Video Saliency: A Large-Scale Benchmark and a New Model
    • 119
    • PDF
    Deep Learning For Video Saliency Detection
    • 8
    • PDF
    Hybrid convolutional neural networks and optical flow for video visual attention prediction
    • 5
    Video Salient Object Detection via Fully Convolutional Networks
    • 363
    • PDF
    Going from Image to Video Saliency: Augmenting Image Salience with Dynamic Attentional Push
    • 21
    • PDF
    End to End Background Subtraction by Deep Convolutional Neural Network
    • Hongwei Sun
    • Computer Science
    • 2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)
    • 2018
    Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency
    • 10
    • PDF
    Viewport-Dependent Saliency Prediction in 360° Video
    • 1
    A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos
    • 109
    • PDF
    Saliency Prediction for 360-degree Video

    References

    SHOWING 1-10 OF 75 REFERENCES
    Shallow and Deep Convolutional Networks for Saliency Prediction
    • 314
    • Highly Influential
    • PDF
    DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations
    • 301
    • PDF
    Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
    • 270
    • PDF
    Saliency detection by multi-context deep learning
    • 665
    • PDF
    SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
    • 364
    • PDF
    Beyond Frame-level CNN: Saliency-Aware 3-D CNN With LSTM for Video Action Recognition
    • 149
    End-to-End Saliency Mapping via Probability Distribution Prediction
    • 108
    • PDF
    Learning Video Saliency from Human Gaze Using Candidate Selection
    • 138
    • PDF
    Temporal spectral residual: fast motion saliency detection
    • 84
    • PDF
    Top down saliency estimation via superpixel-based discriminative dictionaries
    • 29
    • PDF