5 papers
Few-Shot Transformation of Common Actions into Time and Space
Pengwan Yang, Pascal Mettes, Cees G. M. Snoek
This paper introduces the task of few-shot common action localization in time and space. Given a few trimmed support videos containing the same but unknown action, we strive for sp…
Adversarial Self-Supervised Scene Flow Estimation
Victor Zuanazzi, Joris van Vugt, Olaf Booij +1
This work proposes a metric learning approach for self-supervised scene flow estimation. Scene flow estimation is the task of estimating 3D flow vectors for consecutive 3D point cl…
4-Connected Shift Residual Networks
Andrew Brown, Pascal Mettes, Marcel Worring
The shift operation was recently introduced as an alternative to spatial convolutions. The operation moves subsets of activations horizontally and/or vertically. Spatial convolutio…
Using phase instead of optical flow for action recognition
Omar Hommos, Silvia L. Pintea, Pascal S. M. Mettes +1
Currently, the most common motion representation for action recognition is optical flow. Optical flow is based on particle tracking which adheres to a Lagrangian perspective on dyn…
Featureless: Bypassing feature extraction in action categorization
Silvia L. Pintea, Pascal S. Mettes, Jan C. van Gemert +1
This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to th…