TY - GEN
T1 - Recognizing Actions in Videos from Unseen Viewpoints
AU - Piergiovanni, A. J.
AU - Ryoo, Michael S.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and camera viewpoints. In this paper, we show that current convolutional neural network models are unable to recognize actions from camera viewpoints not present in their training data (i.e., unseen view action recognition). To address this, we develop approaches based on 3D representations and introduce a new geometric convolutional layer that can learn viewpoint invariant representations. Further, we introduce a new, challenging dataset for unseen view recognition and show the approaches ability to learn viewpoint invariant representations.
AB - Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and camera viewpoints. In this paper, we show that current convolutional neural network models are unable to recognize actions from camera viewpoints not present in their training data (i.e., unseen view action recognition). To address this, we develop approaches based on 3D representations and introduce a new geometric convolutional layer that can learn viewpoint invariant representations. Further, we introduce a new, challenging dataset for unseen view recognition and show the approaches ability to learn viewpoint invariant representations.
UR - https://www.scopus.com/pages/publications/85123198073
U2 - 10.1109/CVPR46437.2021.00411
DO - 10.1109/CVPR46437.2021.00411
M3 - Conference contribution
AN - SCOPUS:85123198073
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 4122
EP - 4130
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Y2 - 19 June 2021 through 25 June 2021
ER -