arXiv 1906.070162019-06-14cs.CV

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

备注：: arXiv admin note: substantial text overlap with arXiv:1807.00686, arXiv:1710.08011

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。