arXiv Analytics

Sign in

arXiv:1906.07016 [cs.CV]AbstractReferencesReviewsResources

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

Zhaofan Qiu, Dong Li, Yehao Li, Qi Cai, Yingwei Pan, Ting Yao

Published 2019-06-14Version 1

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.

Comments: arXiv admin note: substantial text overlap with arXiv:1807.00686, arXiv:1710.08011
Categories: cs.CV
Related articles: Most relevant | Search more
arXiv:1807.00686 [cs.CV] (Published 2018-06-29)
YH Technologies at ActivityNet Challenge 2018
arXiv:1907.10837 [cs.CV] (Published 2019-07-25)
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
arXiv:2006.11693 [cs.CV] (Published 2020-06-21)
Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020

Links

Toolbox