Katrien Laenen

TL;DR: It is found that the visual and textual item data not only share product features but also contain complementary product features for the outfit recommendation task, confirming the need to effectively combine them into multimodal item representations.

TL;DR: A neural network which learns intermodal representations for fashion attributes to be utilized in a cross-modal search tool and demonstrates that the neural network model trained with the objective function on image fragments acquired with the rule-based segmentation approach improves the results of image search with textual queries.

TL;DR: An attention-based fusion method for outfit recommendation which fuses the information in the product image and description to capture the most important, fine-grained product features into the item representation is described.

TL;DR: A novel approach to conducting passage retrieval for multimodal question answering of ancient artworks where the query image caption of the multi-modal query is provided as additional evidence to state-of-the-art retrieval models in the cultural heritage domain trained on a small dataset.