1^st International Workshop on Video Retrieval Methods and Their Limits

Program

• 9:00 - 9:10 Opening remarks
• 9:10 - 9:55 Invited talk : Object and Entity Recognition for Video Content Understanding

Lei Zhang , Microsoft Corporation, USA

• 9:55 - 10:30 Coffee break

• 10:35 - 11:05 Oral paper : Unsupervised Teacher-Student Model for Large-scale Video Retrieval

Dong Liang, Lanfen Lin, Rui Wang, Jie Shao, Changhu Wang and Yen-Wei Chen

Zhejiang University, China; AI Lab, ByteDance Inc, China; Ritsumeikan University, Japan

• 11:05 - 11:35 Oral paper : Fusion of Multimodal Embeddings for Ad-Hoc Video Search

Danny Francis, Phuong Anh Nguyen, Benoit Huet and Chong-Wah Ngo

EURECOM, Sophia-Antipolis, France; City University of Hong-Kong, Kowloon, Hong Kong

• 11:35 - 12:20 Invited talk : Localizing concepts, the few-shot way

Cees Snoek, University of Amsterdam, The Netherlands

• 12:20 - 13:45 Lunch break

• 13:45 - 14:30 Invited talk : From TRECVid submissions to high-tech startups

Harro Stokman, Kepler Vision Technologies, The Netherlands

• 14:30 - 15:00 Oral paper : Instance-based Video Search via Multi-task Retrieval and Re-ranking

Zhicheng Zhao, Guanyu Chen, Chong Chen, Xinyu Li, Xuanlu Xiang, Yanyun Zhao, and Fei Su

Beijing University of Posts and Telecommunications, China

• 15:00 - 15:45 Invited talk : Fast, Flexible, and Scalable Multimedia Retrieval

Shin’ichi Satoh, National Institute of Informatics, Japan

• 15:45 - 16:05 Coffee break

• 16:05 - 16:25 Short Video : Introducing the Low Altitude Disaster Imagery (LADI) Dataset
• 16:25 - 17:10 Panel Discussion : “What’s Next for Video Retrieval: Directions and Future Challenges”
  • Dima Aldamen, University of Bristol, UK
  • Shin'ichi Satoh, National Institute of Informatics, Japan
  • Lei Zhang, Microsoft Corporation, USA
  • Arslan Basharat, Kitware, USA