vix.ing · top · new · best · stats · spec

Qiniu Submission to ActivityNet Challenge 2018

2018/06/12 by Xiaoteng Zhang, Zhang, Xiaoteng, Yixin Bao +17
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1806.04391

4 pages, 3 figures, CVPR workshop

arxiv created 2018/06/12 · arxiv updated 2018/06/13

Abstract

In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018. In the two tasks, non-local neural networks and temporal segment networks are implemented as our base models. Multi-modal cues such as RGB image, optical flow and acoustic signal have also been used in our method. We also propose new non-local-based models for further improvement on the recognition accuracy. The final submissions after ensembling the models achieve 83.5% top-1 accuracy and 96.8% top-5 accuracy on the Kinetics validation set, 35.81% top-1 accuracy and 62.59% top-5 accuracy on the MIT validation set.

Related