Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction
Abstract
Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc. to produce a robust video-level representation. We here introduce a learnable aggregation technique whose primary objective is to retain short-time temporal structure between frame-level features and their spatial interdependencies in the representation. Also, it can be easily adapted to the cases where there have very scarce training samples. We evaluate the method on a real-fake expression prediction dataset to demonstrate its superiority. Our method obtains 65% score on the test dataset in the official MAP evaluation and there is only one misclassified decision with the best reported result in the Chalearn Challenge (i.e. 66:7%) . Lastly, we believe that this method can be extended to different problems such as action/event recognition in future.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2017
- DOI:
- 10.48550/arXiv.1708.07335
- arXiv:
- arXiv:1708.07335
- Bibcode:
- 2017arXiv170807335O
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- Submitted to International Conference on Computer Vision Workshops