UTSA submission to THUMOS 2015
Junjie Cai, Qi Chuan Tian · 2015
For THUMOS 2015 action recognition task, we submitted one run of our results, which used the features trained from deep neural network. Since testing videos are temporally untrimmed, we applied a sliding window of 100 frames for both validation and test dataset. Video-level scores were generated by maximum pooling of video clips.