NewEvery arXiv paper, its researchers & institutions — mapped.
paper

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

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.

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