Ting Yao, Xue Li
Published 2018-06-29Version 1
This notebook paper presents an overview and comparative analysis of our systems designed for the following five tasks in ActivityNet Challenge 2018: temporal action proposals, temporal action localization, dense-captioning events in videos, trimmed action recognition, and spatio-temporal action localization.
Comments: Rank 2 in both Temporal Activity Detection Task & Kinetics Task @ ActivityNet 2018. arXiv admin note: substantial text overlap with arXiv:1710.08011 by other authors
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020
![QR code for arXiv:1807.00686 [cs.CV]](http://oss.arxitics.com/images/favicon.svg)