Contrastive Learning for Natural Language-Based Vehicle Retrieval

Tam Minh Nguyen, Quang Huu Pham, Linh Bao Doan, Hoang Viet Trinh, Viet-Anh Nguyen, Viet-Hoang Phan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 4245-4252

Abstract


AI City Challenge 2021 Task 5: The Natural Language-Based Vehicle Tracking is a Natural Language-based Vehicle Retrieval task, which requires retrieving a single-camera track using a set of three natural language descriptions of the specific targets. In this paper, we present our methods to tackle the difficulties of the provided task. Experiments with our approaches on the competitive dataset from AICity Challenge 2021 show that our techniques achieve Mean Reciprocal Rank score of 0.1701 on the public test dataset and 0.1571 on the private test dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Nguyen_2021_CVPR, author = {Nguyen, Tam Minh and Pham, Quang Huu and Doan, Linh Bao and Trinh, Hoang Viet and Nguyen, Viet-Anh and Phan, Viet-Hoang}, title = {Contrastive Learning for Natural Language-Based Vehicle Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {4245-4252} }