CVJun 20, 2019

vireoJD-MM at Activity Detection in Extended Videos

arXiv:1906.08547v1
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for surveillance video analysis.

The paper tackled activity detection in extended surveillance videos by exploiting person/vehicle detections and action localization, achieving results through late fusion of components.

This notebook paper presents an overview and comparative analysis of our system designed for activity detection in extended videos (ActEV-PC) in ActivityNet Challenge 2019. Specifically, we exploit person/vehicle detections in spatial level and action localization in temporal level for action detection in surveillance videos. The mechanism of different tubelet generation and model decomposition methods are studied as well. The detection results are finally predicted by late fusing the results from each component.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes