CUHK & SIAT Submission for THUMOS 15 Action Recognition Challenge

By Limin Wang, Zhe Wang, Yuanjun Xiong, Yu Qiao. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jun Liu
2. Limin Wang
3. Yu Qiao
4. Yuanjun Xiong
5. Yanghao Li
6. Pichao Wang
7. Chunhui Liu
8. Cuiling Lan

Citations in the corpus

• PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, methodology): “For action detection, existing methods mainly utilize either sliding-window scheme [46, 31], or action proposal approaches [47].”
• Towards Good Practices for Very Deep Two-Stream ConvNets (2015, methodology): “In this THUMOS15 submission, we train the very deep two-stream ConvNets in the same way as the original two-stream ConvNets [12] without using these [20], without using our proposed good practices) Method Year Accuracy iDT+FV [16] 2013 85.9% iDT+HSV [10] 2014 87.9% MIFS+FV [8] 2015 89.1% TDD+FV…”
• Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, methodology): “A method that divides the continuous sequence into short clips with the shot boundary detected by computing the color histogram and motion histogram was proposed in [11].”