TY - GEN
T1 - Temporal Gaussian mixture layer for videos
AU - Piergiovanni, A. J.
AU - Ryoo, Michael S.
N1 - Publisher Copyright:
© 2019 International Machine Learning Society (IMLS).
PY - 2019
Y1 - 2019
N2 - We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos. The TGM layer is a temporal convolutional layer governed by a much smaller set of parameters (e.g., location/variance of Gaussians) that arc fully diffcrentiable. We present our fully convolutional video models with multiple TGM layers for activity detection. The extensive experiments on multiple datasets, including Charades and MultiTHUMOS, confirm the effectiveness of TGM layers, significantly outperforming the state-of-the-arts1.
AB - We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos. The TGM layer is a temporal convolutional layer governed by a much smaller set of parameters (e.g., location/variance of Gaussians) that arc fully diffcrentiable. We present our fully convolutional video models with multiple TGM layers for activity detection. The extensive experiments on multiple datasets, including Charades and MultiTHUMOS, confirm the effectiveness of TGM layers, significantly outperforming the state-of-the-arts1.
UR - https://www.scopus.com/pages/publications/85078321468
M3 - Conference contribution
AN - SCOPUS:85078321468
T3 - 36th International Conference on Machine Learning, ICML 2019
SP - 9008
EP - 9023
BT - 36th International Conference on Machine Learning, ICML 2019
PB - International Machine Learning Society (IMLS)
T2 - 36th International Conference on Machine Learning, ICML 2019
Y2 - 9 June 2019 through 15 June 2019
ER -