Classification of holoscopic 3D micro-gesture images and videos
W Zhang, W Zhang, J Shao - 2018 13th IEEE International …, 2018 - ieeexplore.ieee.org
W Zhang, W Zhang, J Shao
2018 13th IEEE International Conference on Automatic Face …, 2018•ieeexplore.ieee.orgThis paper presents an empirical study on applying convolutional neural networks (CNNs) to
the Holoscopic Micro-Gesture Recognition Challenge 2018 (HoMGR 2018 [1]). Based on
some neural networks trained on large scale datasets such as ImageNet, we are able to get
fine-tuned models to work well on the HoMGR 2018 data. Result shows that resolution of
inputs is critical for model accuracy. On test sets, the accuracy is 0.867 for frames based
challenge and 0.82 for videos based challenge.
the Holoscopic Micro-Gesture Recognition Challenge 2018 (HoMGR 2018 [1]). Based on
some neural networks trained on large scale datasets such as ImageNet, we are able to get
fine-tuned models to work well on the HoMGR 2018 data. Result shows that resolution of
inputs is critical for model accuracy. On test sets, the accuracy is 0.867 for frames based
challenge and 0.82 for videos based challenge.
This paper presents an empirical study on applying convolutional neural networks (CNNs) to the Holoscopic Micro-Gesture Recognition Challenge 2018 (HoMGR 2018[1]). Based on some neural networks trained on large scale datasets such as ImageNet, we are able to get fine-tuned models to work well on the HoMGR 2018 data. Result shows that resolution of inputs is critical for model accuracy. On test sets, the accuracy is 0.867 for frames based challenge and 0.82 for videos based challenge.
ieeexplore.ieee.org
Showing the best result for this search. See all results