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

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.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment