2017 TREC Video Retrieval Evaluation
Notebook Papers and Slides



TRECVID home  |   TRECVID Publications home

National Institute of Standards and Technology Home Page


TRECVID 2017 Overview Papers and Slides

Final papers will be added as they arrive


Paper: TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning and Hyperlinking (.pdf)
G. Awad, A. Butt, J. Fiscus, D. Joy, A. Delgado -- Information Access Division, National Institute of Standards and Technology, USA
M. Michel -- Data Machines Corp., 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
M. Eskevich -- Radboud University, Netherlands
R. Ordelman -- University of Twente, Netherlands
B. Huet -- EURECOM, Sophia Antipolis, France

Slides: TREC Video Retrieval Evaluation (TRECVID) Introduction (.pdf)
I. Soboroff, A. Butt, A. Ellis, D. Dimmick, J. Fiscus, D. Joy, M. Michel, A. Delgado -- National Institute of Standards and Technology
G. Awad -- NIST, Dakota Consulting, Inc.
A. Smeaton, G. J. F. Jones -- Dublin City University
W. Kraaij -- Leiden University; TNO
G. Quénot -- Laboratoire d'Informatique de Grenoble
S. Strassel, X. Li -- Linguistic Data Consortium
M. Eskevich -- Radboud University
R. Ordelman, R. Aly -- University of Twente
B. Huet -- EURECOM

Slides: TRECVID 2017 Ad-hoc Video Search Task (.pdf)
G. Quénot -- Laboratoire d'Informatique de Grenoble
G. Awad -- NIST, Dakota Consulting, Inc.

Slides: TRECVID 2017 Instance Search Task (.pdf)
W. Kraaij -- Leiden University;TNO
G. Awad , A. Butt -- NIST, Dakota Consulting, Inc.

Slides: TRECVID 2017 Video to Text Description (.pdf)
A. Smeaton -- Dublin City University

G. Awad -- Dakota Consulting, Inc; NIST
A. Butt -- Information Access Division, National Institute of Standards and Technology, USA

Slides: TRECVID 2017 Multimedia Event Detection Task (.pdf)
D. Joy, J. Fiscus, A. Delgado, W. McClinton -- NIST

Slides: TRECVID 2017 Video Hyperlinking Task (.pdf)
M. Eskevich -- CLARIN ERIC
R. Ordelman -- University of Twente
G. J. F. Jones -- Dublin City University
B. Huet -- EURECOM

Slides: Final Workshop items and TRECVID 2018 planning (.pdf)

  • Special talk (Dipl.-Inf. Robert Manthey, Technische Universitat Chemnitz)
    Slides: Algorithm development and evaluation with virtual environments (.pdf)

  • Arete Associates
    Paper: TRECVID 2017: Video to Text Notebook Pages (.pdf)
    B. Lang, D. Lavery, K. Roman, E. Porter -- Arete Associates

  • Beijing University of Posts and Telecommunications, Multimedia Communication and Pattern Recognition Labs
    Paper: BUPT-MCPRL at TRECVID 2017 (.pdf)
    K. Zhou, S. Zhao, S. He, Y. Zhu, Z. Wang, Z. Fan, X. Cao, P. Li, Z. Zhao, Y. Zhao, F. Su -- Multimedia Communication and Pattern Recognition Labs, Beijing University of Posts and Telecommunications, China

  • Carnegie Mellon University; Robert Bosch LLC, Research and Technology Center
    Paper: CMU-UCR-BOSCH @ TRECVID 2017: VIDEO TO TEXT RETRIEVAL (.pdf)
    N. C. Mithun, A. K. Roy-Chowdhury -- Electrical and Computer Engineering, University of California, Riverside, USA
    J. B. Li, D. Samarjit -- Robert Bosch LLC, Research and Technology Center, USA
    F. Metze -- Language Technology Institute, Carnegie Mellon University, Pittsburgh, USA

  • Insight Centre for Data Analytics @ DCU Adapt Centre for Digital Content and Media
    Paper: Dublin City University Participation in the VTT Track at TRECVid 2017 (.pdf)
    H. Afli, J. Du, D. Cosgrove -- Adapt Centre for Digital Content Technology, Dublin City University, Dublin 9, Ireland
    F. Hu, K. McGuinness, N. E. O'Connor, E. A. Sanchez, J. Zhou, A. Smeaton -- Insight Centre for Data Analytics, Dublin City University, Dublin 9, Ireland

    Poster: Exploring Deep Learning Models for Video Captioning (.pdf)

  • The University of Sydney; Zhejiang University
    Paper: DL-61-86 at TRECVID 2017: Video-to-Text Description (.pdf)
    J. Dong, S. Huang, D. Tao -- UBTECH Sydney Artificial Intelligence Centre, University of Sydney, Australia
    D. Xu -- College of Computer Science and Technology, Zhejiang University, China

    Slides: DL-61-86 at TRECVID 2017: Video-to-Text Description (.pdf)

  • EURECOM
    Paper: EURECOM at TRECVID 2017: The Adhoc Video Search (.pdf)
    D. Francis, B. Merialdo, B. Huet -- Data Science Department, EURECOM, Sophia Antipolis, France

  • Politecnico di Torino Eurecom
    Paper: Eurecom-Polito at TRECVID 2017: Hyperlinking task (.pdf)
    B. Huet -- EURECOM, Sophia Antipolis, France
    E. Baralis, P. Garza, M. R. Kavoosifar -- Department of Control and Computer Engineering, Politecnico di Torino, Torino, Italy

    Slides: TRECVID 2017 Hyperlinking task Eurecom-Polito team (.pdf)

  • Florida International University; University of Miami
    Paper: Florida International University - University of Miami TRECVID 2017 (.pdf)
    Y. Yan, Y. Tao, M. Shyu -- Dept. of Electrical and Computer Engineering, University of Miami, FL, USA
    S. Pouyanfar, H. Tian, M. P. Reyes, S. Chen -- School of Computing and Information Sciences, Florida International University, FL, USA
    W. Chen, T. Chen -- School of Electrical and Computer Engineering, Purdue University, IN, USA
    J. Chen -- Miami Palmetto Senior High School, FL, USA

    Slides: FIU-UM at TRECVID 2017: Rectified Linear Score Normalization andWeighted Integration for Ad-hoc Video Search (.pdf)

  • Wuhan University
    Paper: IIPWHU@TRECVID 2017 Surveillance Event Detection (.pdf)
    B. Xu, W. Liao, W. Bao, D. Yang, Z. Chen -- School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China

  • Carnegie Mellon University; Chongqing University of Posts and Telecommunications; Renmin University of China
    Paper: Informedia @ TRECVID 2017 (.pdf)
    J. Chen, J. Liang, J. Liu, A. Hauptmann -- Carnegie Mellon University
    S. Chen, Q. Jin -- Renmin University of China
    C. Gao -- Chongqing University of Posts and Telecommunications

    Slides: INF @ TRECVID2017 Video to Text Description (.pdf)

  • CEA-LIST, LABRI, LIG, LIMSI, LISTIC
    Paper: IRIM at TRECVID 2017: Instance Search (.pdf)
    B. Mansencal, J. Benois-Pineau -- LABRI UMR 5800, Université Bordeaux / CNRS / Bordeaux INP, Talence Cedex, France
    H. Bredin -- CNRS, LIMSI, Université Paris-Saclay, BP 133, 91403 Orsay Cedex, France
    A. Benoit, N. Voiron, P. Lambert -- LISTIC, Domaine Universitaire, BP 80439, 74944 Annecy le vieux Cedex, France
    H. Le Borgne, A. Popescu, A. L. Ginsca -- CEA, LIST, Laboratory of Vision and Content Engineering, Gif-sur-Yvettes, France
    G. Quénot -- Univ. Grenoble Alpes, CNRS, LIG, F-38000 Grenoble, France

    Slides: IRIM at TRECVID 2017: Instance Search (.pdf)

  • IRISA, CNRS, INRIA & INSA Rennes, Univ. Rennes 1
    Paper: IRISA at TrecVid 2017: Beyond Crossmodal and Multimodal Models for Video Hyperlinking (.pdf)
    M. Demirdelen, M. Budnik, G. Sargent, R. Bois, G. Gravier -- IRISA, CNRS, Université de Rennes 1

    Slides: IRISA @ TRECVID2017 Beyond Crossmodal and Multimodal Models (.pdf)

  • Klagenfurt University
    Paper: ITEC-UNIKLU Ad-hoc Video Search Submission 2017 (.pdf)
    M. J. Primus, B. Münzer, K. Schoeffmann -- ITEC - Information Technology, Klagenfurt University, Klagenfurt, Austria

  • Information Technologies Institute, Centre for Research and Technology Hellas
    Paper: ITI-CERTH participation in TRECVID 2017 (.pdf)
    F. Markatopoulou, A. Moumtzidou, D. Galanopoulos, K. Avgerinakis, S. Andreadis, I. Gialampoukidis, S. Tachos, S. Vrochidis, V. Mezaris, I. Kompatsiaris -- Information Technologies Institute/Centre for Research and Technology Hellas, Greece
    I. Patras -- Queen Mary University of London, UK

  • Kobe University; National Institute of Information and Communications Technology (NICT); University of Siegen
    Paper: Kobe University, NICT and University of Siegen at TRECVID 2017 AVS Task (.pdf)
    Z. He, K. Uehara -- Graduate School of System Informatics, Kobe University
    T. Shinozaki -- Center for Information and Neural Networks, National Institute of Information and Communications Technology (NICT)
    K. Shirahama, M. Grzegorzek -- Pattern Recognition Group, University of Siegen

  • Intelligent Signal Processing Laboratory of Korea University
    Paper: KU-ISPL TRECVID 2017 VTT System (.pdf)
    D. Kim, J. Beh, Y. Chen, H. Ko -- Intelligent Signal Processing Laboratory, Korea University

  • National Institute of Informatics; Hitachi, Ltd; University of Information Technology, VNU-HCM, Vietnam (HCM-UIT)
    Paper: NII-HITACHI-UIT at TRECVID 2017 (.pdf)
    S. Phan, B. Renoust, Y. Miyao, S. Satoh -- National Institute of Informatics, Tokyo, Japan
    R. Hinami -- The university of Tokyo, Japan
    M. Tran -- University of Science, VNU-HCMC, Vietnam
    V. Nguyen, T. Mai, T. D. Ngo, D. A. Duong, D. Le -- University of Information Technology, VNU-HCMC, Vietnam
    A. G. Xalabarder -- Universitat Politécnica de Catalunya, Spain
    M. Klinkigt, Y. Watanabe, A. Hiroike -- Hitachi, Ltd., Japan

  • Peking University
    Paper: PKU_ICST at TRECVID 2017: Instance Search Task (.pdf)
    Y. Peng, X. Huang, J. Qi, J. Zhang, J. Zhao, M. Yuan, Y. Zhuo, J. Chi, Y. Yuan -- Institute of Computer Science and Technology, Peking University, China

    Slides: PKU_ICST at TRECVID 2017: Instance Search Task (.pdf)

    Poster: PKU_ICST at TRECVID 2017: Instance Search Task (.pdf)

  • Shandong Normal University
    Paper: Shandong Normal University in the VTT Tasks at TRECVID 2017 (.pdf)
    E. Yu, M. Gao, Y. Li, X. Dong, J. Sun -- School of Information Science and Engineering, Shandong Normal University, China

  • Tianjin University & National University of Singapore
    Paper: Tianjin University and National University of Singapore at TRECVID 2017: Video to Text Description (.pdf)
    A. Liu, Y. Qiu, N. Xu, Y. Su -- School of Electrical and Information Engineering, Tianjin University, China
    Y. Wong -- Smart Systems Institute, National University of Singapore
    M. S. Kankanhalli -- School of Computing, National University of Singapore

  • Tokyo Institute of Technology; National Institute of Advanced Industrial Science and Technology
    Paper: TokyoTech-AIST at TRECVID 2017: Multimedia Event Detection Using Deep CNNs and Zero-Shot Classiers (.pdf)
    N. Inoue, R. Yamamoto, N. Rong, S. Kanai, J. Masada, C. Shiraishi, K. Shinoda -- Tokyo Institute of Technology, Japan
    S. Lee -- National Institute of Advanced Industrial Science and Technology, Japan

    Slides: Multimedia Event Detection using Deep CNNs and Zero-Shot Classifiers (.pdf)

  • Chemnitz University of Technology; University of Applied Sciences Mittweida
    Paper: Technische Universität Chemnitz and Hochschule Mittweida at TRECVID Instance Search 2017 (.pdf)
    S. Kahl, C. Roschke, M. Heinzig, D. Kowerko, M. Ritter -- Junior Professorship Media Computing,Technische Universität Chemnitz,Germany
    D. Richter, M. Eibl, M. Ritter -- Professorship Media Informatics, University of Applied Sciences Mittweida, D-09648 Mittweida, Germany

  • Center of AI, University of Technology Sydney
    Paper:UTS CAI submission at TRECVID 2017 Video to Text Description Task (.pdf)
    G. Li, P. Pan, Y. Yang -- University of Technology Sydney, Australia

  • University of Amsterdam
    Paper:University of Amsterdam and Renmin University at TRECVID 2017: Searching Video, Detecting Events and Describing Video (.pdf)
    C. G. M. Snoek, D. C. Koelma -- University of Amsterdam, Amsterdam, The Netherlands
    X. Li, C. Xu -- Renmin University of China, Beijing, China

    Slides:Multi-Scale Word2VisualVec for Video Caption Retrieval (.pdf)

    Slides:Segments, Residuals and Embeddings for Few-Example Video Event Detection (.pdf)

    Slides:Query Understanding is Key for Zero-Example Video Search (.pdf)

  • NTT Communication Science Laboratories; National Institute of Informatics
    Paper: NTT Communication Science Laboratories and National Institute of Informatics at TRECVID 2017 Instance Search (.pdf)
    H. Nagano, X. Wu, K. Hiramatsu, K. Kashino -- NTT Communication Science Laboratories, NTT corporation, Japan
    S. Satoh -- National Institute of Informatics, Japan

  • City University of Hong Kong
    Paper: VIREO @ TRECVID 2017: Video-to-Text, Ad-hoc Video Search, and Video hyperlinking (.pdf)
    P. A. Nguyen, Q. Li, Z. Cheng, Y. Lu, H. Zhang, C. Ngo -- Video Retrieval Group (VIREO), City University of Hong Kong
    X. Wu -- The School of Information Science and Technology, Southwest Jiaotong University

    Slides:Minimizing risk in video hyperlinking (.pdf)

  • Waseda University; Meisei University
    Paper: Waseda_Meisei at TRECVID 2017: Ad-hoc Video Search (.pdf)
    K. Ueki, K. Hirakawa, K. Kikuchi, T. Ogawa, T. Kobayashi -- Faculty of Science and Engineering, Waseda University, Japan

    Slides: Waseda_Meiseiat TRECVID 2017 Ad-hoc Video Search(AVS) (.pdf)

  • National Engineering Research Center for Multimedia Software, Wuhan University
    Paper: WHU-NERCMS at TRECVID2017: Instance Search Task (.pdf)
    D. Xu, J. Lan, X. Chai, Y. chen, X. Wang, J. Li, L. Jiang, C. Liang -- National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University, China


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

    Last updated:
    Date created: November 20, 2017
    privacy policy / security notice / accessibility statement
    disclaimer / FOIA
    gawad@nist.gov