Chang, X.Liu, W.Huang, P.Y.Li, C.Zhu, F.Han, M.Li, M.Ma, M.Hu, S.Kang, G.Liang, J.Gui, L.Yu, L.Qian, Y.Wen, J.Hauptmann, A.Awad, G.2025-12-182025-12-182019TRECVID 2019: An evaluation campaign to benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & retrieval, 2019 / Awad, G. (ed./s), pp.1-8https://hdl.handle.net/11541.2/41311We propose a video analysis system detecting activities in surveillance scenarios which wins Trecvid Activities in Extended Video (ActEV¹) challenge 2019. For detecting and localizing surveillance events in videos, Argus employs a spatial-temporal activity proposal generation module facilitating object detection and tracking, followed by a sequential classification module to spatially and temporally localize persons and objects involved in the activity. We detail the design challenges and provide our insights and solutions in developing the state-of-the-art surveillance video analysis system.enCopyright 2019 TRECVIDobject detection and trackingsurveillance videoTRECVIDConference paper2-s2.0-85085911536