Human Activity Detection in Multi-Camera, Continuous, Long-Duration Video (HADCV'22) Workshop


ActEV SDL UF Challenge

In this WACV HADCV’22 workshop we will present the research findings of the ActEV Self-Reported Leaderboard (SRL) Challenge .
The ActEV SRL will provide a new test dataset to participants to run developed algorithms on their own computer systems and submit results to a scoring server. By removing the requirement for software submissions to a test-server, we hope to lower the bar for challenge participation relative to the prior Sequestered Data Leaderboard.



Challenge Schedule

  • NIST releases ActEV SRL test dataset: September 10, 2021
  • ActEV SRL Challenge Opens: September 10, 2021
  • Deadline for ActEV SRL results submission: December 01, 2021
  • Invite the top three teams on the ActEV SRL Challenge for the WACV HADCV'22 workshop: December 18, 2021
Contact Us

For any questions about the HADCV'22 workshop, please contact us:
HADCV'22 workshop email: hadcv@nist.gov

Workshop Program
Date: January 4, 2022
Start time : 9:00 AM Hawaii Standard Time (HST) - (GMT ( UTC ): 7:00 PM (19:00))
End time : 16:50 HST

Schedule Item Type Session
(Optional)
Start
Time
Title Speaker/Author(s)
Remarks   09:00 Welcome J. Fiscus / Y. Lee / A. Godil
Keynote/Invited Talk   09:05 Invited Talk: Beyond HADCV -What is Next? Alexander Hauptmann (Carnegie Mellon University)
Session Header ActEV SRL Challenge Results & Top-Performers Session I (0955-1125)  
Oral Paper   09:55 ActEV SRL Challenge Results  J. Fiscus; Y. Lee; A. Delgado; E. Godard; B. Chocot; A. Godil; E. J. Golden; L. Diduch; J. Zhang (NIST)
Oral Paper   10:15 SRL Rank1 - BUPT-MCPRL at ActEV-SRL 2021 : 215AOD   Junfeng Wan; Zhihang Tong; Xiyu Zhao (Beijing University of posts and Telecommunications)
Break   10:30 Morning Break  
Oral Paper   10:45 SRL Rank2 - Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals  Lijun Yu; Yijun Qian; Wenhe Liu; Alexander  Hauptmann (Carnegie Mellon University)
Oral Paper   11:05 SRL Rank3 - GabriellaV2: Towards Better Generalization in Surveillance Videos for Action Detection  Ishan Rajendrakumar Dave; Zacchaeus Scheffer; Akash Kumar; Sarah Shiraz; Yogesh Rawat; Mubarak Shah (University of Central Florida)
Session Header Video Analytics & Infrastructure Session II (1125-1155)  
Oral Paper   11:25 Modelling Ambiguous Assignments for Multi-Person Tracking in Crowds Daniel Stadler (Karlsruhe Institute of Technology); Jürgen Beyerer (Fraunhofer IOSB)
Oral Paper   11:40 From Leaderboard To Operations: DIVA Transition Experiences Bharadwaj Ravichandran; Roderic Collins; Keith Fieldhouse; Kellie N Corona; Anthony Hoogs (Kitware)
Break   11:55 Lunch   
Session Header Activity Detection/Recognition Session III (1315-1450)  
Keynote/Invited Talk   13:15 Invited Talk: DIVA Program Retrospective: Autonomous Detection of (Some) Activities in Security Video Jack Cooper (IARPA)
Oral Paper   14:05 TRM:Temporal Relocation Module for Video Recognition Yijun Qian; Guoliang Kang; Lijun Yu; Wenhe Liu; Alexander Hauptmann (Carnegie Mellon University)
Oral Paper   14:20 Win-Fail Action Recognition Paritosh  Parmar (University of British Columbia); Brendan Morris (University of Nevada)
Oral Paper   14:35 Actor-Centric Tubelets for Real-Time Activity Detection in Extended Videos Effrosyni Mavroudi; Prashast Bindal; Rene Vidal (Johns Hopkins University)
Break   14:50 Afternoon Break 
Session Header Activity Recognition & Video Analytics Session IV (1505-1650)  
Oral Paper   15:05 Sign Pose-based Transformer for Word-level Sign Language Recognition Marek  HRUZ; Matyáš Boháček (University of West Bohemia)
Oral Paper   15:20 Video Action Re-Localization using Spatio-Temporal Correlation Akshaya Ramaswamy; Karthik Seemakurthy; Jayavardhana Gubbi; Balamuralidhar P (TCS Research)
Oral Paper   15:35 PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset Lutao Chu; Yi Liu; Zewu Wu; Shiyu Tang; Guowei Chen; Yuying Hao; Juncai Peng; Zhiliang Yu; Zeyu Chen; Baohua Lai; Haoyi Xiong (Baidu Research)
Keynote/Invited Talk   15:50 Invited Talk: Fine-grained Activities of People Worldwide Jeffrey Byrne (Visym Labs)
Other   16:40 ActEV Challenges and Datasets Group Discussion  

4th International Workshop on Human Activity Detection in multi-camera, Continuous, long-duration Video (HADCV'2022), at the IEEE Winter Conf. on Applications of Computer Vision (WACV'22), Waikoloa, Hawaii, January 4, 2022

Updates
Paper Schedule
  • Paper Submission Due: October 26, 2021 November 01, 2021
New for HADCV’22: ActEV Self-Reported Leaderboard (SRL) Challenge
  • NIST releases ActEV SRL test dataset: September 10, 2021
  • ActEV SRL Challenge Opens: September 10, 2021
  • Deadline for ActEV SRL Challenge results submission: December 01, 2021
  • Invite the top three teams on the ActEV SRL Challenge: December 18, 2021
Summary
The “4th International Workshop on Human Activity Detection in multi-camera, Continuous, long-duration Video (HADCV'22)” 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 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 workshop and presented the results of the ActEV 2018 challenges. In the 2nd WACV HADCV’20, we presented the results of ActEV Known Facility (KF) Sequestered Data Leaderboard (SDL) challenge on the larger and more challenging Multiview Extended Video with Activities (MEVA) KF dataset with more activities than ActEV 2018. In the 3rd WACV HADCV’21 workshop, we presented the research findings of the ActEV Unknown Facility (UF) SDL challenge . In this WACV HADCV’22 workshop we will present the research findings of ActEV Self-Reported Leaderboard (SRL) Challenge. For ActEV SRL, a portion of the MEVA Known Facility sequestered test set will made available for the first time (Sep 10th) and run as a self-reported evaluation, lowering the entry bar for new participants. Training resources for ActEV SRL have been increased with newly released annotations for 160 hours of video totaling 59K activity instances from the MEVA Known Facility dataset , and the Person In Places (PIP) dataset, now totaling 410K annotated instances from a multitude of diverse locations. We will have three invited keynote talks from experts in the field. We will also have three talks from the best performers on the two challenges. Submitted papers will be selected after a double-blind review on topics related to activity detection and will be published in IEEE proceeding of WACV workshop. The workshop will provide a platform for researchers to share research experiences and foster collaboration. The ActEV SRL challenge will start September 10, 2021.
Timeline
01Nov
Paper submission due
19Nov
Camera Ready Papers Due
10Sep
ActEV SRL starts
01Dec
ActEV SDL SRL deadline
Call for Papers

Important Dates:
October 26, 2021 November 01, 2021: 11:00 pm: *Full Paper Submission Due (8 page limit + reference)
October 26, 2021 November 01, 2021: 11:00 pm: *Short Paper Submission Due (4 page limit + reference)
*Accepted papers will be included in the Proceedings of IEEE WACV 2022 and will be part of IEEE Xplore digital library.
November 11, 2021 : Notification to Authors
November 19, 2021 : Camera Ready Papers Due


New for HADCV’22: ActEV Self-Reported Leaderboard (SRL) Challenge

  • NIST releases ActEV SRL Challenge test dataset: September 10, 2021
  • ActEV SRL Challenge Opens: September 10, 2021
  • Deadline for ActEV SRL Challenge results submission: December 01, 2021
  • Invite the top three teams on the ActEV SRL Challenge: December 18, 2021

Jan 04, 2022: HADCV'22 Workshop Date

About the 4th International HADCV Workshop 2022:
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 of the ActEV Self-Reported Leaderboard (SRL) Challenge will be presented. In addition, we are inviting the research community to submit 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
    Alexander G. Hauptmann, CMU
    Jeff Byrne, Visym
    Jack Cooper, IARPA

    Program committee
    Emily M. Hand, UNR
    Keiji Yanai, UEC
    Wenhe Liu, CMU
    Stefanos Vrochidis, CERTH-ITI
    George Awad, Georgetown University
    Fabian Caba Heilbron, Adobe Research
    Mohsen Ali, ITU
    Huijuan Xu, PSU
    Snehasis Mukherjee, Shiv Nadar University
    Keith Curtis, NIST
    Chong-Wah Ngo, CITYU
    Sudeep Sarkar, USF
    Shin'ichi Satoh, NII
    Cosimo Distante, CNR
    Roddy Collins, Kitware
    Bo Li, USM
    Asad Butt, JHU
    Michael Ryoo, SUNY
    Waqas Sultani, ITU
    Kimiaki Shirahama, Kindai
    Paper Submissions


    Authors are invited to submit work not currently under consideration elsewhere. The HADCV'20 workshop submission are handled via HADCV22 CMT page HADCV22 workshop CMT link

    Accepted papers (both full or short) will be allocated 8 pages for full paper or 4 pages for short paper in the proceeding (plus 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 and will be part of the IEEE Xplore digital library.


    For WACV'22 Paper preparation and Author kit, see the a href="http://wacv2022.thecvf.com/submission">WACV'22 Submissions page for more details.

    Workshop Registration
    You can register for HADCV'22 workshop at the WACV'22 registration page or by clicking this link: WACV2022 Registration




    If you have any question about the HADCV'22 Workshop, please email to hadcv@nist.gov