2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDARS-4.9
Paper Title SEMANTIC-PRESERVING METRIC LEARNING FOR VIDEO-TEXT RETRIEVAL
Authors Sungkwon Choo, Seong Jong Ha, Joonsoo Lee, NCSOFT, Republic of Korea
SessionARS-4: Re-Identification and Retrieval
LocationArea I
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Image and Video Analysis, Synthesis, and Retrieval: Image & Video Storage and Retrieval
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Video-text retrieval requires finding an optimal space for comparing the similarity of two different modalities. Most approaches adopt ranking loss as a primary training objective to find the space. The loss is only interested in bringing the samples annotated as pairs closer to each other without considering the semantic relevance of different samples. This rather causes even semantically similar pairs not to get close. To deal with the problem, we propose semantic-preserving metric learning. The proposed method entails the metric space where the similarity ratio between samples is proportional to semantic relevance between annotations. In the extensive experiments on video-text datasets, the proposed method presents a close alignment between the learned metric space and the semantic space. It also demonstrates state-of-the-art retrieval performance.