Dialogue-to-Video Retrieval
This addresses the need for better video recommendation systems in social media and web contexts, though it appears incremental as it builds on existing dialogue-based retrieval tasks.
The paper tackles the problem of retrieving videos based on dialogue queries, presenting a novel system that improves retrieval performance by up to 15.8% on R@1 over a previous model and outperforms the state-of-the-art by up to 6.0% on R@10.
Recent years have witnessed an increasing amount of dialogue/conversation on the web especially on social media. That inspires the development of dialogue-based retrieval, in which retrieving videos based on dialogue is of increasing interest for recommendation systems. Different from other video retrieval tasks, dialogue-to-video retrieval uses structured queries in the form of user-generated dialogue as the search descriptor. We present a novel dialogue-to-video retrieval system, incorporating structured conversational information. Experiments conducted on the AVSD dataset show that our proposed approach using plain-text queries improves over the previous counterpart model by 15.8% on R@1. Furthermore, our approach using dialogue as a query, improves retrieval performance by 4.2%, 6.2%, 8.6% on R@1, R@5 and R@10 and outperforms the state-of-the-art model by 0.7%, 3.6% and 6.0% on R@1, R@5 and R@10 respectively.