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

Source: [Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications](<https://www.sota2.com/research/paper/68fa7a6c1e209131cea831b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:59:41.376Z

Authors: Noreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Published: 2025-08-06T20:37:24.000Z

## 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 general 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 it achieved state-of-the-art performance in average precision (AP) and recall, demonstrating the effectiveness of multi-modal query adaptation and dual-stream attention. Source code is at: \\href{https://github.com/DET-LIP/DAMM}{GitHub}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.04868>)

[PDF](<https://arxiv.org/pdf/2508.04868.pdf>)
