Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications


Noreen Anwar (LITIV, Polytechnique Montréal), Guillaume-Alexandre Bilodeau (LITIV, Polytechnique Montréal), Wassim Bouachir (Université du Québec (TELUQ))
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)

Abstract

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a novel framework introducing both query adaptation and structured cross-attention for improved accuracy and efficiency. DAMM capitalizes on three types of queries: appearance-based queries from vision-language models, positional queries using polygonal embeddings, and random learned queries for broader scene coverage. Furthermore, a dual-stream cross-attention module separately refines semantic and spatial features, boosting localization precision in cluttered scenes. We evaluated DAMM on four challenging benchmarks and DAMM achieves state-of-the-art performance in average precision (AP) and recall, demonstrating the effectiveness of multi-modal query adaptation and dual-stream attention.

Citation

@inproceedings{Anwar_2025_BMVC,
author    = {Noreen Anwar and Guillaume-Alexandre Bilodeau and Wassim Bouachir},
title     = {Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_131/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection