VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)

In this paper, we describe the system developed for Activities in Extended Video(ActEV) task at TRECVid 2019 [1] and the achieved results. Activities in Extended Video(ActEV): The goal of Activities in Extended Video is to spatially and temporally localize the action instances in a surveillance sett...

Full description

Saved in:
Bibliographic Details
Main Authors: HOU, Zhijian, PAN, Ying-Wei, YAO, Ting, NGO, Chong-wah
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6492
https://ink.library.smu.edu.sg/context/sis_research/article/7495/viewcontent/VireoJD_mm_actev.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7495
record_format dspace
spelling sg-smu-ink.sis_research-74952022-01-10T05:04:06Z VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV) HOU, Zhijian PAN, Ying-Wei YAO, Ting NGO, Chong-wah In this paper, we describe the system developed for Activities in Extended Video(ActEV) task at TRECVid 2019 [1] and the achieved results. Activities in Extended Video(ActEV): The goal of Activities in Extended Video is to spatially and temporally localize the action instances in a surveillance setting. We have participated in previous ActEV prize challenge. Since the only difference between the two challenges is evaluation metric, we maintain previous pipeline [2] for this challenge. The pipeline has three stages: object detection, tubelet generation and temporal action localization. This time we extend the system for two aspects separately: better object detection and advanced two-stream action classification. We submit 2 runs, which are summarised below. - VireoJD-MM Pipeline1: This run achieves Partial AUDC=0.6012 using advanced two-stream action classification. It has been recognized in many papers [3, 4] that two-stream structure increases action recognition performance. In our prize challenge model, we only use RGB frames as input. For the submission this time, we extend the action classification stage into an advanced two-stream action classification module. - VireoJD-MM SecondarySystem: This run achieves Partial AUDC=0.6936 using better object detection model. The CMU team released the groundtruth of object bounding box provided by Kitware as well as their object detection and tracking code1 based on VIRAT dataset. They build a system to detect and track small objects in outdoor scenes for surveillance videos. For the submission this time, we replace our object detection and tracking code with their code and keep the remaining stages of tubelet generation and temporal action localization. 2019-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6492 https://ink.library.smu.edu.sg/context/sis_research/article/7495/viewcontent/VireoJD_mm_actev.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Graphics and Human Computer Interfaces
spellingShingle Graphics and Human Computer Interfaces
HOU, Zhijian
PAN, Ying-Wei
YAO, Ting
NGO, Chong-wah
VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
description In this paper, we describe the system developed for Activities in Extended Video(ActEV) task at TRECVid 2019 [1] and the achieved results. Activities in Extended Video(ActEV): The goal of Activities in Extended Video is to spatially and temporally localize the action instances in a surveillance setting. We have participated in previous ActEV prize challenge. Since the only difference between the two challenges is evaluation metric, we maintain previous pipeline [2] for this challenge. The pipeline has three stages: object detection, tubelet generation and temporal action localization. This time we extend the system for two aspects separately: better object detection and advanced two-stream action classification. We submit 2 runs, which are summarised below. - VireoJD-MM Pipeline1: This run achieves Partial AUDC=0.6012 using advanced two-stream action classification. It has been recognized in many papers [3, 4] that two-stream structure increases action recognition performance. In our prize challenge model, we only use RGB frames as input. For the submission this time, we extend the action classification stage into an advanced two-stream action classification module. - VireoJD-MM SecondarySystem: This run achieves Partial AUDC=0.6936 using better object detection model. The CMU team released the groundtruth of object bounding box provided by Kitware as well as their object detection and tracking code1 based on VIRAT dataset. They build a system to detect and track small objects in outdoor scenes for surveillance videos. For the submission this time, we replace our object detection and tracking code with their code and keep the remaining stages of tubelet generation and temporal action localization.
format text
author HOU, Zhijian
PAN, Ying-Wei
YAO, Ting
NGO, Chong-wah
author_facet HOU, Zhijian
PAN, Ying-Wei
YAO, Ting
NGO, Chong-wah
author_sort HOU, Zhijian
title VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
title_short VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
title_full VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
title_fullStr VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
title_full_unstemmed VireoJD-MM @ TRECVID 2019: Activities in extended video (ACTEV)
title_sort vireojd-mm @ trecvid 2019: activities in extended video (actev)
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/6492
https://ink.library.smu.edu.sg/context/sis_research/article/7495/viewcontent/VireoJD_mm_actev.pdf
_version_ 1770575975303610368