2022 TREC Video Retrieval Evaluation
Notebook Papers and Slides

Dublin City University
Paper: DCU ADAPT at TRECVID 2022: Deep Video Understanding Challenge (.pdf)
A. Potyagalova, G. J. F. Jones -- ADAPT Centre, School of Computing, Dublin City University, Ireland

Slides: DCU ADAPT at TRECVID 2022 Deep Video Understanding Challenge (.pdf)

Beijing University of Posts and Telecommunications
Paper: BUPT-MCPRL at TRECVID 2022 (.pdf)
H. Zhao, Z. Tong, Y. Xiao, S. Qian, S. Li, Z. Tian, Y. Zhao, F. Su, Z. Zhao -- Beijing University of Posts and Telecommunications, China

Slides: BUPT-MCPRL at TRECVID 2022 ActEV SRL Challenge (.pdf)

Columbia University, Graphen Inc, and Microsoft Corporation
Paper: Semantic Understanding and Evolving Interaction Tracking in Long-form Multimodal Datasets(.pdf)
V. Anand Y. Dong, R. Ramesh, Z. Chen, L. Li, C. Lin -- Columbia University, USA
Y. Chen -- Graphen Inc.

Slides: Semantic Understanding with Interaction Tracking in Long-form Multimodal Sources(.pdf)

Elyadata
Paper: Elyadata TRECVID 2022 VTT Model(.pdf)
H. Elleuch, F. Bougares, A. Badri -- ELYADATA, Tunisia

Poster: Elyadata TRECVID 2022 VTT Model(.pdf)

Information Technologies Institute, Centre for Research and Technology Hellas
Paper: ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2022(.pdf)
K. Gkountakos, D. Galanopoulos, D. Touska, K. Ioannidis, S. Vrochidis, V. Mezaris, I. Kompatsiaris -- Information Technologies Institute, Centre for Research and Technology Hellas, Greece

Slides: ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2022. Human and vehicle activity detection and recognition from untrimmed videos(.pdf)
Slides: Combining textual and visual features into multiple joint latent spaces, and introducing dual softmax re ranking, for Ad hoc Video Search(.pdf)

Kindai University; Osaka Gakuin University; Osaka University
Paper: Kindai University, Osaka Gakuin University and Osaka University at TRECVID 2022 AVS Task(.pdf)
K. Shirahama, K. Fujioka, T. Shinno -- Kindai University, Japan
T. Matsubara -- Graduate School of Engineering Science, Osaka University, Japan
K. Uehara -- Department of Business Administration, Osaka Gakuin University, Japan

Slides: kindai_ogu_osaka at TRECVID 2022 AVS Task: A Hierarchical Approach to Dynamically Treat Meanings of Words and Phrases(.pdf)

Nagaoka University of Technology
Paper: Nagaoka University of Technology Submissions to TRECVID 2022 Video to Text Task(.pdf)
T. Mashimo, M. Ishii, T. Yukawa -- Nagaoka University of Technology, Niigata, Japan

Slides: Nagaoka University of Technology at TRECVID 2022: Video to Text(.pdf)

National Institute of Informatics, Japan; University of Information Technology, VNU-HCMC, Vietnam
Paper: NII_UIT at TRECVID 2022: Movie Summarization Task(.pdf)
N. Nguyen, T. H. Nguyen, C. N. Thanh, H. Vo, K. Le, T. Mai, T. PhamNguyen, D. Le -- University of Information Technology, VNU-HCM, Vietnam
S. Satoh -- National Institute of Informatics, Japan

Slides: NII_UIT at TRECVID 2022: Movie Summarization Task(.pdf)

Peking University
Paper: PKU_WICT at TRECVID 2022: Disaster Scene Description and Indexing Task(.pdf)
Y. Chen, H. Hsu, J. Ye, Z. Yang, Z. Wang, X. He, Y. Peng -- Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China

Slides: PKU_WICT at TRECVID 2022: Disaster Scene Description and Indexing Task(.pdf)

Renmin University of China
Paper: RUCAIM3-Tencent at TRECVID 2022: Video to Text Description(.pdf)
Z. Yue, Y. Liu, L. Zhang, L. Yao, Q. Jin -- Renmin University of China, China

Slides: RUCAIM3-Tencent at TRECVID 2022: Video to Text Description(.pdf)
Poster: Leveraging VLP models for cross modal video retrieval(.pdf)

Renmin University of China
Paper: Renmin University of China at TRECVID 2022: Improving Video Search by Feature Fusion and Negation Understanding(.pdf)
X. Li, A. Chen, Z. Wang, F. Hu, K. Tian, X. Chen, C. Dong -- Renmin University of China, China

Slides: Feature Fusion and Negation Understanding for Ad-hoc Video Search(.pdf)

Tokyo Institute of Technology
Paper: Tokyo Tech at TRECVID 2022: Multi-Stage Framework for Video Action Detection(.pdf)
R. P. Amorim, N. Inoue, K. Shinoda -- Tokyo Institute of Technology

John Hopkins University and University of Maryland
Paper: A proposal-based solution to spatio-temporal action detection in untrimmed videos(.pdf)
K. Shah, R. Chellappa -- John Hopkins University, USA
J. Gleason -- University of Maryland, College Park, USA

Slides: A proposal-based solution to spatio-temporal action detection in untrimmed videos(.pdf)

University of Missouri-Kansas City
Paper: University of Missouri-Kansas City TRECVID 2022 DSDI Track(.pdf)
Y. Tao -- University of Miami, USA
S. Chen, M. Shyu -- University of Missouri-Kansas City, USA

Carnegie Mellon University
Paper: CMU-VIDION: MODIFIED BLIP WITH AUDIO FOR VIDEO TO TEXT DESCRIPTION(.pdf)
L. J. Yao, J. B. Li, F. Metze -- Carnegie Mellon University, USA

Slides: CMU-VIDION: Modified BLIP with Audio for Video to Text Description(.pdf)

City University of Hong Kong
Paper: VIREO @ TRECVID 2022 Ad-hoc Video Search(.pdf)
J. Wu -- City University of Hong Kong
Z. Ma, C. Ngo -- Singapore Management University

Waseda University; Meisei University; SoftBank Corporation
Paper: Waseda_Meisei_SoftBank at TRECVID 2022 (.pdf)
K. Ueki -- Department of Information Science, Meisei University, Japan; Faculty of Science and Engineering, Waseda University
Y. Suzuki, H. Takushima, H. Okamoto, H. Tanoue, T. Hori -- SoftBank Corp., Japan

Slides: Waseda_Meisei_SoftBank at TRECVID 2022 Video to Text Description(.pdf)
Slides: Waseda_Meisei_SoftBank at TRECVID 2022 Ad-hoc Video Search(.pdf)
Slides: Waseda_Meisei_SoftBank at TRECVID 2022 Activities in extended videos(.pdf)

Wuhan University
Paper: WHU-NERCMS AT TRECVID2022 : DEEP VIDEO UNDERSTANDING TASK(.pdf)
A. Lu, J. Guo, K. Zhao, Y. Sun, R. Li, C. Liang -- National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University

Slides: WHU-NERCMS @ TRECVID 2022 : DEEP VIDEO UNDERSTANDING TASK(.pdf)

Hangzhou Dianzi University
Paper: MLVC_HDU@TRECVID 2022: Video to Text (VTT) and Activities in Extended Video (ActEV) Tasks(.pdf)
P. Li, T. Wang, X. Ye -- School of Computer Science, Hangzhou Dianzi University Hangzhou, China

Poster: Dynamic Interactive Aggregation Network for TRECVID'22 ActEV Task(.pdf)
Poster: Semantic Alignment Network for Video Captioning(.pdf)