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.
TRECVID2022 Agenda
TRECVID2022 | December 06-09, 2022 | Eastern Standard Time (EST)
-
Introduction and welcome
Speaker(s)
- Ian Soboroff, NIST
-
Ad-hoc Video Search - Task Overview
Speaker(s)
-
Georges Quenot, LABORATOIRE D'INFORMATIQUE DE GRENOBLE
-
Waseda_Meisei_SoftBank at TRECVID 2022: Ad-hoc video search
Speaker(s)
- Kazuya Ueki , Meisei University
-
Feature Fusion and Negation Understanding for Ad-hoc Video Search
Speaker(s)
- Aozhu Chen, Renmin University of China
- Ziyue Wang, Renmin University of China
- Fan Hu, Renmin University of China
- Kaibin Tian, Renmin University of China
- Xirong Li, Renmin University of China
-
Combining textual and visual features into multiple joint latent spaces, and introducing dual softmax re-ranking, for Ad-hoc Video Search
Speaker(s)
- Damianos Galanopoulos, Centre for Research & Technology Hellas, Information Technology Institute, CERTH-ITI
-
BREAK
-
kindai_ogu_osaka at TRECVID 2022 AVS Task: A Hierarchical Approach to Dynamically Treat Meanings of Words and Phrases
Speaker(s)
- Kimiaki Shirahama, Faculty of Informatics, Kindai University
-
Poster: Leveraging VLP Models for Cross-modal Video Retrieval
Speaker(s)
- Yuqi Liu, Renmin University of China
-
AVS Task Discussion
-
Keynote Talk: Toward Fairer Multimodal information systems
Speaker(s)
- Vivek Singh, Rutgers University
-
BREAK
-
OpenMFC 2022 Workshop Opening Remarks
Speaker(s)
- Jim Horan, NIST
-
OpenMFC Invited keynote: A Brief Overview of Recent Advancement of Generative AI and New Challenges to Deepfake Detection
Speaker(s)
- Jun-Cheng Chen , Research Center for Information Technology Innovation, Academia Sinica
-
BREAK
-
OpenMFC 2022 Evaluation Program
Speaker(s)
- Haiying Guan, NIST
-
OpenMFC 2022 Evaluation Infrastructure
Speaker(s)
- Lukas Diduch, NIST/Dakota Consulting Inc.
-
Open Discussion
-
MSUM - Task Overview
Speaker(s)
- Keith Curtis, NIST
-
NII_UIT at TRECVID 2022: Movie Summarization Task
Speaker(s)
- Duy-Dinh Le, University of Information Technology, VNU-HCMC
-
MSUM Task Discusssion
-
Video-to-Text - Task Overview
Speaker(s)
- Asad Butt, NIST
-
RUCAIM3-Tencent at TRECVID 2022: Video to Text Description
Speaker(s)
- Zihao Yue, Renmin University of China
-
BREAK
-
Nagaoka University of Technology at TRECVID 2022: Video to Text
Speaker(s)
- Mutsuki Ishii, Nagaoka University of Technology
- Toshichika Mashimo, Nagaoka University of Technology
-
Waseda_Meisei_SoftBank at TRECVID 2022: Video-to-text
Speaker(s)
- Hiroki Takushima, SoftBank Corp.
-
Modified BLIP with Audio for Video to Text
Speaker(s)
- Laura Yao, Carnegie Mellon University
- Juncheng Li, Carnegie Mellon University
-
Poster: Semantic Alignment Network for Video Captioning
Speaker(s)
- Ping Li, Hangzhou Dianzi University, China
-
Poster: ELYADATA TRECVID 2022 VTT MODEL
Speaker(s)
- Haroun Elleuch, Elyadata
-
VTT Task Discussion
-
BREAK
-
Keynote Talk : Learning, Understanding and Interaction in Videos
Speaker(s)
- Manmohan Chandraker, University of California San Diego
-
BREAK
-
OpenMFC - Keynote: Mobile steganography: Looking to the future
Speaker(s)
- Professor Jennifer L. Newman, Iowa State University
-
OpenMFC 2022 Deepfakes Challenge Data
Speaker(s)
- Baptiste Chocot, NIST
- Ghorbanian Bajgiran, NIST
-
OpenMFC 2022 Workshop Closing Remarks
Speaker(s)
- Yooyoung Lee, NIST
-
Activities in Extended Videos - Task Overview
Speaker(s)
- Jonathan Fiscus, NIST
-
An Effective Framework for Activity Detection in Untrimmed Security Videos
Speaker(s)
- Hangyue Zhao, Beijing University of Posts and Telecommunications, China
-
Human and vehicle activity detection and recognition from untrimmed videos
Speaker(s)
- Despoina Touska, Centre for Research & Technology Hellas, Information Technology Institute, CERTH-ITI
-
A proposal-based solution to spatio-temporal action detection in untrimmed videos
Speaker(s)
- Ketul Shah , Johns Hopkins University
-
Waseda_Meisei_SoftBank at TRECVID 2022: Activities in extended videos
Speaker(s)
- Hideaki Okamoto, SoftBank Corp.
-
Poster: Dynamic Interactive Aggregation Network for TRECVID’22 ActEV Task
Speaker(s)
- Xingchao Ye, Hangzhou Dianzi University, China
-
BREAK
-
ActEv Task Discussion
-
Disaster Scene Description and Indexing - Task Overview
Speaker(s)
- Jeffrey Liu, MIT Lincoln Laboratory
-
PKU_WICT at TRECVID 2022: Disaster Scene Description and Indexing Task
Speaker(s)
- Xiangteng He, Peking University, China
-
DSDI Task Discussion
-
Keynote Talk: Large-scale learning from multimodal videos
Speaker(s)
- Cordelia Schmid, INRIA / Google Research
-
Deep Video Understanding - Task Overview
Speaker(s)
- George Awad, NIST
-
Semantic Understanding with Interaction Tracking in Long-form Multimodal Sources
Speaker(s)
- Vishal Anand, Microsoft Corporation, Columbia University
-
BREAK
-
WHU-NERCMS at TRECVID 2022: Deep Video Understanding Task
Speaker(s)
- Jiahao Guo, Wuhan University, China
-
TREC Video Retrieval Evaluation (TRECVID-2022) Deep Video Understanding Challenge
Speaker(s)
- Anastasia Potyagalova, Dublin City University, Ireland
-
DVU Task Discussion
-
New Task Proposal : Towards Answering Health-related Questions from Medical Videos
Speaker(s)
- Deepak Gupta, National Library of Medicine, National Institutes of Health
-
New Task Proposal: Valence, Arousal, Norm, and Emotion Evaluation
Speaker(s)
- Audrey Tong, NIST
-
TRECVID 2023 - Planning and Final Remarks
Speaker(s)
- George Awad, NIST