U.S. flag

An official website of the United States government

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.

Back to Event Page

TRECVID Agenda

Note: This is the DRAFT Agenda. Please check back for updates.

Workshop Schedule:

TRECVID will be held in the morning section: 7:00am -11:00am EST

OpenMFC Agenda

OpenMFC will be held in the afternoon section: 11:30am - 3:30pm EST

-
Introduction and Welcome
Speaker(s)
  • Ian Soboroff, NIST
-
Ad-hoc Video Search - Task Overview
Speaker(s)
  • Georges Quenot, LABORATOIRE D'INFORMATIQUE DE GRENOBLE
-
Unlikelihood learning for interpretable embedding
Speaker(s)
  • Wu Jiaxin, City University of Hong Kong
-
Kuaishou at TRECVID 2021: Two-stage Ranking Strategy for Ad-hoc Video Search
Speaker(s)
  • Fangming Zhou, Renmin University of China; Kuaishou Technology
-
Visual and Textual Encoder Assembly for Ad-hoc Video Search
Speaker(s)
  • Aozhu Chen, Renmin University of China
-
Waseda_Meisei_SoftBank at TRECVID 2021: Ad-hoc video search
Speaker(s)
  • Ueki Kazuya, Meisei University
-
Break
-
Ad-hoc Video Search - Task Discussion
Speaker(s)
  • Coordinators/Teams,
-
Video-to-Text - Task Overview
Speaker(s)
  • Asad Butt and Yvette Graham, NIST; Trinity College Dublin
-
RUC AIM3 at TRECVID 2021: Video to Text Description
Speaker(s)
  • Liang Zhang, Renmin University of China
-
Multi-Level Visual Representation with Reinforced Adversarial Learning for Video Description Generation
Speaker(s)
  • Chengbo Dong, Renmin University of China
-
Automatic Generation of Video Descriptions Using DenseNet
Speaker(s)
  • Mutsuki Ishii, Nagaoka University of Technology
-
Video-to-Text - Task Discussion
Speaker(s)
  • Coordinators/Teams,
-
Break
-
OpenMFC

(OpenMFC Agenda)

See More
-
Keynote Talk: Learning Representations from Sign Language Videos
Speaker(s)
  • Xavier Giro Nieto, Universitat Politecnica de Catalunya (UPC)
-
Activities in Extended Video - Task Overview
Speaker(s)
  • Yooyoung Lee, NIST
-
CMU Informedia at TRECVID 2021: Towards Better Spatial-Temporal Activity Detection
Speaker(s)
  • Wenhe Liu, Language Technologies Institute, Carnegie Mellon University
-
215AD: A Comprehensive Activity Detection for Surveillance Videos in TRECVID 2021 ActEV Challenge
Speaker(s)
  • Binyu Zhang, Multimedia Communication and Pattern Recognition Labs, Beijing University of Posts and Telecommunications
-
Break
-
GabriellaV2: UCF DIVA system
Speaker(s)
  • Zacchaeus Scheffer, University of Central Florida
-
Multi-label activity recognition in extended videos using objects' Spatio-temporal boundaries
Speaker(s)
  • Konstantinos Gkountakos and Despoina Touska, Information Technologies Institute, Centre for Research and Technology Hellas
-
Activities in Extended Video - Task Discussion
Speaker(s)
  • Coordinators/Teams,
-
OpenMFC

(OpenMFC Agenda)

See More
-
Disaster Scene Description and Indexing - Task Overview
Speaker(s)
  • Jeffrey Liu, MIT Lincoln Laboratory
-
Florida International University - University of Miami TRECVID 2021 DSDI Track
Speaker(s)
  • Maria E. Presa-Reyes, Knight Foundation School of Computing and Information Sciences Florida International University, Miami, FL ; Department of Electrical and Computer Engineering
-
Low altitude Image analysis using panoptic segmentation
Speaker(s)
  • Emmanouil Christakis, Visual Computing Lab - Center for Research and Technology Hellas (VCL-CERTH)
-
Keynote Talk: The Drone Data Conundrum
Speaker(s)
  • Jarlath O’Neil-Dunne, Spatial Analysis Laboratory, University of Vermont | USDA Forest Service R&D
-
Break
-
DSDI Discussion
Speaker(s)
  • Coordinators/Teams,
-
Video Summarization - Task Overview
Speaker(s)
  • Keith Curtis and Gareth Jones, NIST; Dublin City University
-
DCU ADAPT at TRECVID 2021: Video Summarization - Keeping It Simple
Speaker(s)
  • Anastasia Potyagalova, ADAPT Centre, School of Computing, Dublin City University
-
Zero-Shot Classification of Events for Character-Centric Video Summarization
Speaker(s)
  • Alison Reboud, Eurecom
-
NII_UIT Team at TRECVID 2021 - VSUM Task
Speaker(s)
  • Duy-Dinh Le, University of Information Technology, VNU-HCMC
-
Movie Summarization - Task Proposal
Speaker(s)
  • Coordinators/Teams,
-
OpenMFC

(OpenMFC Agenda)

See More
-
Instance Search - Task Overview
Speaker(s)
  • George Awad, NIST
-
WHU-NERCMS in Trecvid INS 2021
Speaker(s)
  • Chao Liang, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University
-
BUPT_MCPRL at TRECVID 2021 - Instance Search Task
Speaker(s)
  • Wenhao Yang, Beijing University of Posts and Telecommunications
-
Deep Video Understanding - Grand Challenge
Speaker(s)
  • George Award, NIST
-
Language Modelling with Knowledge Graphs on Long-form Multi-Modal Inputs
Speaker(s)
  • Vishal Anand, Columbia University; Microsoft Corp.
-
Multi Task Analysis for Deep Video Understanding
Speaker(s)
  • Beibei Zhang, Nanjing University
-
Break
-
Deep Video Understanding - Task Proposal
Speaker(s)
  • George Award, NIST
-
TRECVID 2022 - Future Plans and Conclusions
Speaker(s)
  • Coordinators/Teams,
-
OpenMFC

(OpenMFC Agenda)

See More