Program

The workshop will be conducted on October 16, 2021.

All times are in EDT (Montreal time)

8:00 - 8:10 Opening remarks

8:10 - 9:00 Invited talk: Video Retrieval and Description by Natural Language
Qin Jin, Professor, School of Information, Renmin University of China, China

9:00 - 9:50 Invited talk: Video Search and Retrieval Challenges and Opportunities
Giuseppe Amato, Senior Researcher - ISTI - Consiglio Nazionale delle Ricerche

9:50 - 10:05 Oral paper: What Matters for Ad-hoc Video Search? A Large-scale Evaluation on TRECVID

Aozhu Chen; Fan Hu; Zihan Wang; Fangming Zhou; Xirong Li

Renmin University of China

10:05 - 10:30 Coffee break

10:30 - 10:45 Oral paper: Instance Search via Fusing Hierarchical Multi-level Retrieval and Human-object Interaction Detection

Wenhao Yang; Yinan Song; Zhicheng Zhao; Fei Su

Beijing University of Posts and Telecommunications

10:45 - 11:00 Oral paper: Hard-Negatives or Non-Negatives? A Hard-Negative Selection Strategy for Cross-Modal Retrieval Using the Improved Marginal Ranking Loss

Damianos Galanopoulos; Vasileios Mezaris

Information Technologies Institute, Centre for Research of Technology Hellas

11:00 - 11:50 Invited talk: From Narrations to Semantic Similarity for Cross-Modal Video Retrieval

Dima Damen, Associate Professor, Department of Computer Science, Visual Information Laboratory, University of Bristol, UK

11:50 - 12:00 Conclusion