Skip to main content

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Human Activity Detection in Multi-Camera, Continuous, Long-Duration Video (HADCV'21) Workshop


ActEV SDL UF Challenge

In this WACV HADCV’21 workshop we plan to present the research findings of the ActEV SDL Unknown Facility (UF) challenge:

Challenge Timeline:

  • September 21, 2020 : ActEV SDL UF Challenge Starts
  • November 27, 2020 :Deadline for SDL UF CLI submission
  • December 20, 2020 : Top two teams on the ActEV'21 SDL UF (with Known Activities) leaderboard invited to give oral presentations at the workshop
  • Contact Us

    For any questions about the HADCV'21 workshop, please contact us:
    HADCV'21 workshop email: hadcv@nist.gov

    HADCV'21 Virtual Workshop Program
    Date: January 5, 2021
    Start time : 8:00 AM Pacific Standard Time (PST)

    --- --

    Schedule Item Type

    Session

    (Optional)

    Start

    Time (PST)

    Title

    Speaker/Author(s)

    Remarks

     

    08:00

    Welcome

    Jon Fiscus, NIST

    Invited Talk

     

    08:15

    MEVA: A Large-Scale Multiview, Multimodal Video Dataset For Activity Recognition: TBA

    Roderic Collins, Kitware

    Other

     

    08:50

    Q/A Discussion

    Break

     

    9:00

    Break (10 min)

    Session Header

    ActEV SDL  Unknown Facility (UF) Challenge Results & Best Performer Presentations (9:10-10:25)

    Oral Presentation

     

    09:10

    ActEV SDL UF Challenge Summary and Results 

    Yooyoung Lee, NIST

    Oral Presentation

     

    09:35

    Real-time Activity Detection in Unknown Facilities with Dense Spatio-temporal Proposals

    Lijun Yu and Wenhe Liu, CMU

    Oral Presentation

     

    10:00

    Aspects of real-live action detection : Architectures – Efficiency – Zero-shot learning

    Hilde Kuehne, IBM

    Break

     

    10:25

    Break (35 min)

    Session Header

    Activity Detection Session (11:00-12:15)

     

    Keynote/Invited Talk

     

    11:00

    Keynote Talk: The ASAPS Challenge: Contest 2 -  Real-time Public Safety Emergency Analysis from Streaming Multimodal Data

    John Garofolo and Craig Connelly, NIST

    Other

     

    11:40 AM

    ActEV SDL Challenges and Datasets Group Discussion (20 min)

     

    Session Header

    Poster Session (12:00-12:15)

    Poster Presentation

    7 min

    12:00

    PeR-ViS: Person Retrieval in Video Surveillance using Semantic Description

    Parshwa Shah, Arpit Garg, Vandit Gajjar

    Poster Presentation

    7 min

    12:07

    2020 Sequestered Data Evaluation for Known Activities in Extended Video: Summary and Results

    Afzal Godil, Yooyoung Lee, Jon Fiscus, Andrew Delgado, Eliot Godard, Baptiste Chocot, Lukas Diduch, Jim Golden, Jesse Zhang


    The 3rd International Workshop on
    Human Activity Detection in multi-camera, Continuous, long-duration Video (HADCV'21)
    under the IEEE Winter Conf. on Applications of Computer Vision (WACV)
    Virtual Conference, January 5, 2021

    Updates
    • September 21, 2020 : ActEV SDL UF Challenge starts
    • November 27, 2020 :Deadline for SDL UF CLI submission
    • December 20, 2020 : Top two teams on the ActEV'21 SDL UF (with Known Activities) leaderboard invited to give oral presentations at the workshop
    • November 06, 2020 : Workshop Paper submission deadline (updated)
    Summary
    The “3rd International Workshop on Human Activity Detection in multi-camera, Continuous, long-duration Video (HADCV'21)” will focus on human activity detection in multi-camera video streams. The ability to detect human activities is an important task in computer vision due to its potentially wide range of applications such as public safety and security, crime prevention, traffic monitoring and control, eldercare/childcare, human-computer interaction, human-robot interaction, hospital activity monitoring, and many more. The ActEV (Activities in Extended Video) series [1] of challenges started in 2018 to foster development of robust, multi-camera, automatic activity detection algorithms for forensic and real-time alerting applications. We successfully organized the 1st WACV HADCV'19 [1] workshop and presented the results of the ActEV 2018 challenges.

    In the 2nd WACV HADCV’20 [2], we presented the results of ActEV Sequestered Data Leaderboard (SDL) Known Facility (KF) challenge [21] on the larger and more challenging Multiview Extended Video with Activities (MEVA) KF dataset (mevadata.org) with more activities than ActEV 2018. In this WACV HADCV’21 workshop we plan to present the research findings of the ActEV SDL Unknown Facility (UF) challenge [22]. The UF challenge will include detection of activities which are known to the participant's system a priori as well as activities that are presented to the system at test time (surprise/ad_hoc activities) on a new sequestered dataset. We will have two invited keynote talks from experts in the field. We will also have two talks from the best performers on the ActEV SDL UF challenge. Up to four regular papers will be selected after a double-blind review on topics related to activity detection. The workshop will provide a platform for researchers to share research experiences and foster collaboration. The ActEV SDL UF challenge (https://actev.nist.gov/sdl) dataset will start on September 21, 2020.

    In this workshop, we will bring diverse stakeholders (activity detection, object detection and tracking, pose estimation, machine learning, etc.) together to help advance the state-of-the-art in human activity detection technology in multi-camera video streaming environments. For this workshop, we will primarily focus on activity detection algorithms, performance evaluation and characterization, and large dataset collections for activity detection. Research findings from the ActEV SDL UF challenge will be presented.

    Timeline
    06Nov
    Paper submission deadline
    20Nov
    Paper Notification
    30Nov
    Camera Ready Papers Due
    21Sep
    ActEV SDL UF starts
    27Nov
    ActEV SDL UF CLI deadline
    Call for Papers

    Important Dates:
    November 06, 2020 : 11:00pm: Paper Submission Due* (8 page limit + reference)
    *Accepted papers will be included in the Proceedings of IEEE WACV 2021 & Workshops and will be sent for inclusion into the IEEE Xplore digital library.
    November 20, 2020 : Notification to Authors
    November 30, 2020 : Camera Ready Papers Due

    September 21, 2020: ActEV SDL UF Competition Starts
    November 27, 2020: ActEV SDL UF CLI submission Deadline
    December 20, 2020 : Top two teams on the ActEV'21 SDL UF (with Known Activities) leaderboard invited to give oral presentations at the workshop

    Jan 05, 2021: Virtual HADCV'21 Workshop Date

    About the 3rd International HADCV Workshop 2021:
    This workshop aims to bring all the stakeholders (activity detection, object detection and tracking, pose estimation, machine learning, etc.) together to help advance the state-of-the-art in human activity detection technology in multi-camera video streaming environments. The primary focus will be on activity detection algorithms, performance evaluation and characterization, and large dataset collections for activity detection. Research findings from the ActEV Unknown Facility (UF) challenge will be presented. In addition, we are inviting the research community to submit unpublished research papers which will be published in the IEEE Digital Library on the following topics:

  • Activity detection in untrimmed video
  • Activity detection, recognition, classification and prediction
  • Surprise/Ad-hoc activity detection
  • Multi-camera object detection and tracking in crowded scenes
  • Human activity and behavior analysis in indoor/outdoor environments for public safety, security, traffic monitoring and control, etc.
  • Human activity monitoring in public spaces
  • Person re-identification
  • Human pose estimation and gesture recognition
  • Human activity understanding
  • Spatio-temporal activity/object localization
  • Human behavior and activity analysis
  • Anomaly detection in indoor/outdoor activities
  • Human-human and Human-object interaction
  • Indexing and retrieval of human activity in video datasets
  • Multi-camera analysis
  • Evaluation criteria and metrics for Activity detection
  • Benchmarking datasets and annotations
  • Machine learning/deep learning methods for activity detection
  • Big video datasets
  • Ontology of human Activity
  • Applications of activity detection and understanding in public safety and security, traffic monitoring and control, crime prevention, etc.

  • As organizers of the workshop we are looking forward to contributions in these and related areas.
    A. Godil, J. Fiscus, Y. Lee, A. Hoogs, R. Meth
    People

    Organizers
    Afzal Godil, NIST
    Jonathan G. Fiscus, NIST
    Yooyoung Lee, NIST
    Anthony Hoogs, Kitware
    Reuven Meth, SAIC
    Invited Speakers
    Kate Saenko, Boston University
    John Garofolo, NIST

    Program committee
    Emily M. Hand, UNR
    Marc Ritter, HS-Mittweida
    George Awad, Georgetown University
    Benjamin S. Riggan, UNL
    Cees Snoek, UVA
    Fabian Caba Heilbron, Adobe Research
    Chenqiang Gao, CQUPT
    Waqas Sultani, ITU
    Chong-Wah Ngo, CITYU
    Snehasis Mukherjee, IIIT
    Keith Curtis, NIST
    Carlos Castillo, JHU
    Sudeep Sarkar, USF
    Shin'ichi Satoh, NII
    Cosimo Distante, CNR
    Roddy Collins, Kitware
    Bo Li, USM
    Juefei Yuan, USM
    Asad Butt, JHU
    Pavan Turaga, ASU
    Josh Gleason, UMD
    Fatih Porikli, Australian National University
    Mohsen Ali, ITU
    Hilde Kuehne, IBM
    Cheng Xiangqian, BUPT
    Yu Kong, RIT
    Submissions


    Authors are invited to submit original work not currently under consideration elsewhere. The HADCV'20 workshop submission are handled via HADCV21 CMT page HADCV21 workshop CMT link

    Accepted papers will be allocated 8 pages in the proceeding and that is, a paper can be up to 8 pages + the references. The manuscripts should be submitted in PDF format and should follow the requirements of the IEEE WACV paper format. All work submitted to WACV workshop is considered confidential until the papers appear. Accepted papers will be included in the Proceedings of IEEE WACV 2021 & Workshops and will be sent for inclusion into the IEEE Xplore digital library.


    For WACV'21 Paper preparation and Author kit, See WACV'21 Submissions page for more details Paper preparation and see Author kit.

    Workshop Registration
    You can register for HADCV'21 workshop at the WACV'21 registration page or by clicking this link: WACV2021 Registration




    If you have any question about the HADCV'21 Workshop, please email to hadcv@nist.gov