DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition

By Lin Sun, K. Jia, Tsung-Han Chan, Yuqiang Fang, G. Wang, Shuicheng Yan. 2014

130 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Action Recognition using Visual Attention (2015, neutral): “B-51 Hollywood2 (acc %) (mAP %) Spatial stream ConvNet (Simonyan & Zisserman, 2014) 40.5 - Soft attention model (Our model) 41.3 43.9 Composite LSTM Model (Srivastava et al., 2015) 44.0 - DL-SFA (Sun et al., 2014) - 48.1 Two-stream ConvNet (Simonyan & Zisserman, 2014) 59.4 - VideoDarwin (Fer”
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning (2016, methodology): “While not rivaling supervised methods, this approach, and others that rely on temporal coherence, have achieved some measure of success, pointing to the potential of learning useful representations from video [15, 27, 30, 50, 55].”
Deep Learning for Health Informatics (2017, background): “To identify different activities, [90] proposes to combine deep”
Spectral Inference Networks: Unifying Spectral Methods With Deep Learning (2018, methodology): “SFA has primarily been applied to train shallow models, and when trained on deep models is typically trained in a layer-wise fashion, rather than end-to-end [19, 32].”
Spectral Inference Networks: Unifying Deep and Spectral Learning (2018, methodology): “SFA has primarily been applied to train shallow or linear models, and when trained on deep models is typically trained in a layer-wise fashion, rather than end-to-end (Kompella et al., 2012; Sun et al., 2014).”
An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos (2018, background): “SFA has been well known in pattern recognition and has been applied to the problem of activity recognition [58], [59].”
Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders (2016, unknown): “Deep networks have been used to learn slow feautures in the past [10], but to our knowledge our work is the first to do so in a fully probabilistic way.”
Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition (2017, unknown): “1 Sun [32] 86.”
3D-based Deep Convolutional Neural Network for action recognition with depth sequences (2016, methodology): “The only difference is that [15] used ISA, while Lin et al.[16] employed 160”
Multi-region Two-Stream R-CNN for Action Detection (2016, unknown): “Popular video representations are bag-of-visual-words (BoW) [25] and its variants which aggregate local video features [2], CNN representations [22, 26], and slow feature representations [27].”
Deep Feature Flow for Video Recognition (2016, methodology): “This observation has been used to regularize the feature learning in videos [45, 21, 51, 49, 40].”