Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions

@article{Sudhakaran2017ConvolutionalLS,
  title={Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions},
  author={Swathikiran Sudhakaran and O. Lanz},
  journal={2017 IEEE International Conference on Computer Vision Workshops (ICCVW)},
  year={2017},
  pages={2339-2346}
}
In this paper, we present a novel deep learning based approach for addressing the problem of interaction recognition from a first person perspective. The proposed approach uses a pair of convolutional neural networks, whose parameters are shared, for extracting frame level features from successive frames of the video. The frame level features are then aggregated using a convolutional long shortterm memory. The hidden state of the convolutional long short-term memory, after all the input video… Expand
22 Citations
First-Person Action Recognition With Temporal Pooling and Hilbert–Huang Transform
  • 3
A correlation based feature representation for first-person activity recognition
  • 8
  • PDF
Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos
  • 6
  • PDF
Three-Stream Fusion Network for First-Person Interaction Recognition
  • 2
  • Highly Influenced
  • PDF
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
  • PDF
Attention in Convolutional LSTM for Gesture Recognition
  • 28
  • PDF
Residual Stacked RNNs for Action Recognition
  • 2
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 48 REFERENCES
Pooled motion features for first-person videos
  • 153
  • PDF
Long-term recurrent convolutional networks for visual recognition and description
  • 3,519
  • Highly Influential
  • PDF
Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks
  • 378
  • PDF
Going Deeper into First-Person Activity Recognition
  • 217
  • PDF
Two-Stream Convolutional Networks for Action Recognition in Videos
  • 4,471
  • PDF
Action and Interaction Recognition in First-Person Videos
  • 34
  • Highly Influential
  • PDF
First Person Action Recognition Using Deep Learned Descriptors
  • 125
  • PDF
Unsupervised Learning of Video Representations using LSTMs
  • 1,606
  • PDF
Compact CNN for indexing egocentric videos
  • 84
  • PDF
...
1
2
3
4
5
...