2020 TREC Video Retrieval Evaluation
Notebook Papers and Slides



TRECVID home  |   TRECVID Publications home

National Institute of Standards and Technology Home Page


TRECVID 2020 Overview Papers and Slides

All papers and slides will be updated with final versions as they arrive


This is a DRAFT overview paper. The complete overview paper will be added in the next few month

Paper: TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains (.pdf)
G. Awad, A. Butt, K. Curtis, J. Fiscus, A. Godil, Y. Lee, A. Delgado, J. Zhang, E. Godard, B. Chocot -- Information Access Division, National Institute of Standards and Technology, USA
L. Diduch -- Dakota-Consulting, Inc, USA
J. Liu -- MIT Lincoln Laboratory, USA
A. F. Smeaton, Y. Graham, G. J. F. Jones -- Dublin City University, Ireland
W. Kraaij -- Leiden University; TNO, Netherlands
G. Quénot -- Laboratoire d'Informatique de Grenoble, France

Slides: TREC Video Retrieval Evaluation (TRECVID) Introduction (.pdf)
I. Soboroff, K. Curtis, A. Ellis, D. Dimmick, J. Fiscus, Y. Lee, A. godil, A. Delgado, J. Zhang, E. Godard,, B. Chocot -- National Institute of Standards and Technology
G. Awad -- NIST; Georgetown University.
A. Butt -- NIST; John Hopkins University
L. Diduch -- NIST; Dakota Consulting, Inc
A. Smeaton, Y. Graham, G. Jones -- Dublin City University
W. Kraaij -- Leiden University; TNO
G. Quénot -- Laboratoire d'Informatique de Grenoble
J. Liu -- MIT Lincoln Laboratory

Slides: TRECVID 2020 Ad-hoc Video Search Task (.pdf)
G. Quénot -- Laboratoire d'Informatique de Grenoble
G. Awad -- NIST; Georgetown University

Slides: TRECVID 2020 Instance Search Task (.pdf)
W. Kraaij -- Leiden University;TNO
G. Awad -- NIST; Georgetown University
K. Curtis -- NIST

Slides:TRECVID 2020 Video to Text Description (.pdf)
A. Butt -- NIST; John Hopkins University
G. Awad -- NIST; Georgetown University
Y. Graham -- Dublin City University

Slides: TRECVID 2020 Video Summarization Task (.pdf)
G. Jones -- Dublin City University;TNO
K. Curtis -- NIST

Slides: TRECVID 2020 Disaster Scene Description and Indexing Task (.pdf)
A. Butt -- NIST; John Hopkins University
J. Liu -- MIT Lincoln Laboratory
G. Awad -- NIST; Georgetown University

  • University of Augsburg
    Paper: Transforming Videos to Text (VTT Task) Team: MMCUniAugsburg(.pdf)
    P. Harzig, M. Einfalt, K. Ludwig, R. Lienhart -- University of Augsburg, Germany

  • Beijing University of Posts and Telecommunications
    Paper: BUPT-MCPRL at TRECVID 2020: INS (.pdf)
    Q. Zhang, J. Zhang, Z. Zhao, Y. Zhao, F. Su -- Beijing University of Posts and Telecommunications, China

    Paper: BUPT-MCPRL at TRECVID 2020: ActEV (.pdf)
    X. Zhao, Q. Cao, X. Cheng, J. Wan, Y. Du, B. Zhang, Y. Zhao, Z. Zhao, F. Su -- Beijing University of Posts and Telecommunications, China
    H. Chen -- China Mobile Research Institute, China

  • University of North Texas
    Paper: Application of Very Deep Neural Nets to Videos Depicting Extreme Events (.pdf)
    Y. Li, H. Wang, S. Sun, B. Buckles -- University of North Texas, USA

  • EURECOM and Aalto University
    Paper: Using Fan-Made Content, Subtitles and Face Recognition for Character-Centric Video Summarization (.pdf)
    I Harrando, A. Reboud, P. Lisena, R. Troncy -- EURECOM, France
    J. Laaksonen, A. Virkkunen, M. Kurimo -- Aalto University, Finland

    Slides: Using Fan-Made Content, Subtitles and Face Recognition for Character-Centric Video Summarization(.pdf)
  • Korea University
    Paper: KU-ISPL TRECVID 2020 VTT Model (.pdf)
    J. Lee, Y. Jin, G. Kim, H. Ko -- Intelligent Signal Processing Laboratory, Korea University

  • Florida International University; University of Miami
    Paper: Florida International University - University of Miami TRECVID 2020 DSDI Track(.pdf)
    M. Presa-Reyes, S. Chen -- Florida International University, USA
    Y. Tao, M. Shyu -- University of Miami, USA

  • The University of Electro-Communications
    Paper: UEC at TRECVID 2020: INS and ActEV(.pdf)
    S. Mizuno, K. Yanai -- The University of Electro-Communications, Tokyo , Japan

    Poster: TRECVID2020@UEC(.pdf)
  • University of Chile; Millennium Institute Foundational Research on Data (IMFD)
    Paper: IMFD IMPRESEE at TRECVID 2020: Description Generation by Visual-Syntactic Embedding(.pdf)
    J. Perez-Martin, B. Bustos, J. Perez, J. M. Barrios -- University of Chile

    Slides: Improving Video Captioning with Temporal Composition of a Visual-Syntactic Embedding(.pdf)
  • Carnegie Mellon University
    Paper: CMU Informedia at TRECVID 2020: Activity Detection with Dense Spatio-temporal Proposals(.pdf)
    L. Yu, Y. Qian, W. Liu, A. G. Hauptmann -- Carnegie Mellon University

  • Tokyo Institute of Technology
    Paper: Tokyo Tech at TRECVID 2020: Relation Modeling for Video Action Detection(.pdf)
    R. P. Amorim, N. Inoue, K. Shinoda -- Tokyo Institute of Technology

    Slides: Tokyo Tech at TRECVID 2020: Relation Modeling for Video Action Detection(.pdf)
  • University of Technology Sydney
    Paper: UTS Submission at the TRECVID 2020 Disaster Scene Description and Indexing Task(.pdf)
    Q. Rao, L. Zhu, Y. Yang -- University of Technology Sydney, Australia

  • Information Technologies Institute, Centre for Research and Technology Hellas
    Paper: ITI-CERTH participation in TRECVID 2020(.pdf)
    K. Gkountakos, D. Galanopoulos, M. Mpakratsas, D. Touska, A. Moumtzidou, K. Ioannidis, I. Gialampoukidis, S. Vrochidis, V. Mezaris, I. Kompatsiaris -- Information Technologies Institute, Centre for Research and Technology Hellas, Greece

    Slides: Analysis of tracked objects for detecting activities in extended videos using 3D-CNN architectures(.pdf)
    Poster: ITI-CERTH participation in TRECVID 2020(.pdf)
  • Kindai University and Osaka Gakuin University
    Paper: Kindai University and Osaka Gakuin University at TRECVID 2020 AVS and ActEV Tasks(.pdf)
    D. Mukai, R. Utsunomiya, S. Utsuki, K. Shirahama -- Department of Informatics, Kindai University
    T. Matsubara -- Graduate School of Engineering Science, Osaka University
    K. Uehara -- Department of Business Administration, Osaka Gakuin University

    Poster: Event Detection in Videos Using a Graph Convolutional Network(.pdf)
  • Nagaoka University of Technology, Nagaoka
    Paper: Automatic Caption Generation for Video Clips Using Keyframe and Document Summarization Techniques(.pdf)
    M. Hoshino, T. Yukawa -- Nagaoka University of Technology, Japan

    Poster: Automatic Caption Generation for Video Clips Using Keyframe and Document Summarization Techniques(.pdf)
  • National Institute of Informatics, Japan University of Information Technology, VNU-HCMC, Vietnam
    Paper: NII_UIT AT TRECVID 2020(.pdf)
    D. Le, H. Vo, D. Nguyen, T. Do, T. Pham, T. Vo, T. Nguyen, V. Nguyen, T. Ngo -- University of Information Technology, VNU-HCMC, Vietnam
    Z. Wang, S. Satoh -- National Institute of Informatics, Japan

    Slides: NII-UIT at TRECVID 2020: Video Summarization Task(.pdf)
  • National Institute of Information and Communications Technology;National Institute of Informatics
    Paper: Is AutoML a practical way of tackling DSDI Task?(.pdf)
    S. Iwasawa, K. Uchimoto, Y. Kidawara -- National Institute of Information and Communications Technology, Japan
    S. Satoh -- NICT / National Institute of Informatics, Japan

  • Hitachi, Ltd
    Paper: Hitachi at TRECVID DSDI 2020(.pdf)
    S. Okazaki, Q. Kong, T. Yoshinaga -- Lumada Data Science Lab., Hitachi, Ltd
    M. Klinkigt -- Future Design Lab, Minatomirai Research Center, KYOCERA Corporation

    Slides: Hitachi at TRECVID DSDI 2020(.pdf)
  • Aalto University School of Science
    Paper: PicSOM Experiments in TRECVID 2020(.pdf)
    J. Laaksonen, Z. Guo -- Aalto University School of Science, Finland

    Slides: PicSOM Team's Lessons Learned in TRECVID 2020 VTT(.pdf)
  • Peking University
    Paper: PKU_WICT at TRECVID 2020: Instance Search Task(.pdf)
    Y. Peng, Z. Ye, J. Zhang, H. Sun -- Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China

  • Renmin University of China
    Paper: RUC_AIM3 at TRECVID 2020: Ad-hoc Video Search & Video to Text Description(.pdf)
    Y. Zhao, Y. Song, S. Chen, Q. Jin -- Renmin University of China, China

    Slides: RUC_AIM3 at TRECVID 2020: Ad-hoc Video Search(.pdf)
    Slides: RUC_AIM3 at TRECVID 2020: Video to Text Description(.pdf)
  • Renmin University of China
    Paper: University of China at TRECVID 2020: Sentence Encoder Assembly for Ad-hoc Video Search(.pdf)
    X. Li, F. Zhou, A. Chen -- Renmin University of China, China

    Slides: Sentence Encoder Assembly for Ad-hoc Video Search(.pdf)
  • LINKS Foundation
    Paper: Independent Category Classifiers for Emergency Scene Description using Deep Learning approaches(.pdf)
    M. Zaffaroni -- University of Turin, Italy
    F. Oldani, C. Rossi -- LINKS Foundation, Italy

    Slides: Independent Category Classifiers for Emergency Scene Description using Deep Learning approaches(.pdf)
  • University of Central Florida
    Paper: UCF-System: Activity Detection in Untrimmed Videos(.pdf)
    I. Dave, Z. Scheffer, P. Tirupattur, Y. Rawat, M. Shah -- University of Central Florida

  • City University of Hong Kong
    Paper: VIREO @ TRECVID 2020: Ad-hoc Video Search(.pdf)
    J. Wu, P. A. Nguyen, C. Ngo -- City University of Hong Kong

    Slides: Concept Search Versus Embedding Search(.pdf)
  • Information Technologies Institute, Centre for Research and Technology Hellas
    Paper: Towards low-altitude image analysis: Object-enhanced concept detection (.pdf)
    E. Christakis, S. Demertzis, K. Stavridis, A. Psaltis, A. Dimou, P. Daras -- Visual Computing Lab, Information Technologies Institute, Greece

    Slides: Visual Computing Lab @ TRECVID 2020 Disaster Scene Description and Indexing (DSDI)(.pdf)
  • Wuhan University and Guilin University of Electronic Technology
    Paper: WHU-NERCMS AT TRECVID2020: INSTANCE SEARCH TASK(.pdf)
    J. Yang, K. Chen, Y. Niu, X. Fan, C. Liang -- National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University

  • Waseda University; Meisei University; SoftBank Corporation
    Paper: Waseda_Meisei_SoftBank at TRECVID 2020: Ad-hoc Video Search (.pdf)
    K. Ueki, R. Mutou -- Department of Information Science, Meisei University, Japan
    T. Hori -- Global Information and Telecommunication Institute, Waseda University; SoftBank Corp., Japan
    Y. Kim, Y. Suzuki -- AI Solution Division, 5G & IoT Solution Division, SoftBank Corp., Japan

    Poster: Zero-shot video retrieval using concept-based and visual-semantic embedding approaches(.pdf)
  • XinHuaZhiYun Inc; State Key Laboratory of Media Convergence Production Technology and Systems
    Paper: TRECVID 2020 AVS: Solution of ZY_BJLAB Team (.pdf)
    K. Cui, H. Liu, C. Wang, C. Xu -- XinHuaZhiYun Inc.
    Y. Jiang -- State Key Laboratory of Media Convergence Production Technology and Systems

  • Indian Institute of Space Science and Technology (IIST), Thiruvananthapuram Development and Educational Communication Unit (DECU), Indian Space Research Organisation (ISRO)
    Paper: Attention based caption augmented W2VV++ Adhoc Video Search (AVS) trecvid task (.pdf)
    R. Sharma -- DECU, ISRO Ahmedabad, India
    D. Mishra -- Avionics Department,IIST, Thiruvananthapuram, Kerala, Indias
    H. Bhatt -- SAC, ISRO Ahmedabad, India


  • National Institute of Standards and Technology Home Page
    is an agency \ of the U.S. Commerce Department

    Last updated: Wednesday, 16-Dec-2020 12:54:22 MST
    Date created: December 14, 2020
    privacy policy / security notice / accessibility statement
    disclaimer / FOIA
    gawad@nist.gov