The Library
Variational recurrent sequence-to-sequence retrieval for stepwise illustration
Tools
Tools
Tools
Batra, Vishwas, Haldar, Aparajita, He, Yulan, Ferhatosmanoglu, Hakan, Vogiatzis, George and Guha, Tanaya (2020) Variational recurrent sequence-to-sequence retrieval for stepwise illustration. In: Advances in Information Retrieval : 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part I. Lecture Notes in Computer Science, 12035 . Springer, pp. 50-64. ISBN 9783030454388
|
PDF
WRAP-variational-recurrent-sequence-to-sequence-retrieval-stepwise-illustration-Batra-2020.pdf - Accepted Version - Requires a PDF viewer. Download (4Mb) | Preview |
Official URL: http://dx.doi.org/10.1007/978-3-030-45439-5_4
Abstract
We address and formalise the task of sequence-to-sequence (seq2seq) cross-modal retrieval. Given a sequence of text passages as query, the goal is to retrieve a sequence of images that best describes and aligns with the query. This new task extends the traditional cross-modal retrieval, where each image-text pair is treated independently ignoring broader context. We propose a novel variational recurrent seq2seq (VRSS) retrieval model for this seq2seq task. Unlike most cross-modal methods, we generate an image vector corresponding to the latent topic obtained from combining the text semantics and context. This synthetic image embedding point associated with every text embedding point can then be employed for either image generation or image retrieval as desired. We evaluate the model for the application of stepwise illustration of recipes, where a sequence of relevant images are retrieved to best match the steps described in the text. To this end, we build and release a new Stepwise Recipe dataset for research purposes, containing 10K recipes (sequences of image-text pairs) having a total of 67K image-text pairs. To our knowledge, it is the first publicly available dataset to offer rich semantic descriptions in a focused category such as food or recipes. Our model is shown to outperform several competitive and relevant baselines in the experiments. We also provide qualitative analysis of how semantically meaningful the results produced by our model are through human evaluation and comparison with relevant existing methods.
| Item Type: | Book Item | ||||||
|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
| Library of Congress Subject Headings (LCSH): | Programming languages (Electronic computers)—Semantics, Data sets , Sequential processing (Computer science) | ||||||
| Series Name: | Lecture Notes in Computer Science | ||||||
| Publisher: | Springer | ||||||
| ISBN: | 9783030454388 | ||||||
| ISSN: | 0302-9743 | ||||||
| Book Title: | Advances in Information Retrieval : 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part I | ||||||
| Official Date: | 8 April 2020 | ||||||
| Dates: |
|
||||||
| Volume: | 12035 | ||||||
| Page Range: | pp. 50-64 | ||||||
| DOI: | 10.1007/978-3-030-45439-5_4 | ||||||
| Status: | Peer Reviewed | ||||||
| Publication Status: | Published | ||||||
| Reuse Statement (publisher, data, author rights): | The final authenticated version is available online at http://dx.doi.org/10.1007/978-3-030-45439-5_4 | ||||||
| Access rights to Published version: | Open Access (Creative Commons) | ||||||
| Date of first compliant deposit: | 21 April 2020 | ||||||
| Date of first compliant Open Access: | 22 April 2020 | ||||||
| Related URLs: | |||||||
| Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
