Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019

2019/06/14 by Qiu, Zhaofan, Li, Dong, Li, Yehao +3
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1906.07016

Abstract

This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and spatio-temporal action localization.

Related

• YH Technologies at ActivityNet Challenge 2018
• Action recognition in real-world videos
• Three Branches: Detecting Actions With Richer Features
• The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
• UC Merced Submission to the ActivityNet Challenge 2016