Video Action Recognition with an Additional End-To-End Trained Temporal Stream
- IBM
- ASAPP
- Lawrence Livermore National Laboratory
- Research Organization:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC52-07NA27344
- OSTI ID:
- 1573164
- Report Number(s):
- LLNL-CONF-795738; 994520
- Resource Relation:
- Conference: Waikoloa Village, HI, United States
- Country of Publication:
- United States
- Language:
- English
Similar Records
Accelerating Deep Neural Network Training for Action Recognition on a Cluster of GPUs
Video Summarization Using Deep Action Recognition Features and Robust Principal Components Analysis
Fast neural network training on a cluster of GPUs for action recognition with high accuracy
Conference
·
2018
·
OSTI ID:1489473
+2 more
Video Summarization Using Deep Action Recognition Features and Robust Principal Components Analysis
Conference
·
2020
·
OSTI ID:1734633
+1 more
Fast neural network training on a cluster of GPUs for action recognition with high accuracy
Journal Article
·
2019
· Journal of Parallel and Distributed Computing
·
OSTI ID:1669241
+3 more