Image search using multilingual texts: a cross-modal learning approach between image and text

Abstract

Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images and texts into a unique distributional vector space, enabling to search images by using text queries expressing information needs related to the (visual) content of images, as well as using image similarity. Our framework forces the representation of an image to be similar to the representation of the text that describes it. Moreover, by using multilingual embeddings we ensure that words from two different languages have close descriptors and thus are attached to similar images. We provide experimental evidence of the efficiency of our approach by experimenting it on two datasets: Common Objects in COntext (COCO) [19] and Multi30K [7].

References in corpus (5)

• Distributed Representations of Words and Phrases and their Compositionality
• Skip-Thought Vectors
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• An Autoencoder Approach to Learning Bilingual Word Representations
• Finding beans in burgers: Deep semantic-visual embedding with localization

Cited by in corpus (3)

• Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning
• Graphcore C2 Card performance for image-based deep learning application: A Report
• Towards Zero-shot Cross-lingual Image Retrieval and Tagging