# Qiniu Submission to ActivityNet Challenge 2018

Source: [Qiniu Submission to ActivityNet Challenge 2018](<https://www.sota2.com/research/paper/68fa64811e209131cea04f0f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:05:03.439Z

Authors: Xiaoteng Zhang, Yixin Bao, Feiyun Zhang, Kai Hu, Yicheng Wang, Liang Zhu, Qinzhu He, Yining Lin, Jie Shao, Yao Peng

Published: 2018-06-12T08:42:55.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1806.04391>)

[PDF](<https://arxiv.org/pdf/1806.04391.pdf>)