All You Can Embed: Natural Language Based Vehicle Retrieval With Spatio-Temporal Transformers

Carmelo Scribano, Davide Sapienza, Giorgia Franchini, Micaela Verucchi, Marko Bertogna; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 4253-4262

Abstract

Combining Natural Language with Vision represents a unique and interesting challenge in the domain of Artificial Intelligence. The AI City Challenge Track 5 for Natural Language-Based Vehicle Retrieval focuses on the problem of combining visual and textual information, applied to a smart-city use case. In this paper, we present All You Can Embed (AYCE), a modular solution to correlate single-vehicle tracking sequences with natural language. The main building blocks of the proposed architecture are (i) BERT to provide an embedding of the textual descriptions, (ii) a convolutional backbone along with a Transformer model to embed the visual information. For the training of the retrieval model, a variation of the Triplet Margin Loss is proposed to learn a distance measure between the visual and language embeddings. The code is publicly available at https://github.com/cscribano/AYCE_2021.

Related Material

[pdf]
[bibtex]
@InProceedings{Scribano_2021_CVPR, author = {Scribano, Carmelo and Sapienza, Davide and Franchini, Giorgia and Verucchi, Micaela and Bertogna, Marko}, title = {All You Can Embed: Natural Language Based Vehicle Retrieval With Spatio-Temporal Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {4253-4262} }