Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (1)

Search Parameters:
Keywords = Dual-Path CSDETR

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
14 pages, 12408 KB  
Article
Dual-Path CSDETR: Cascade Stochastic Attention with Object-Centric Priors for High-Accuracy Fire Detection
by Dongxing Yu, Bing Han, Xinyi Zhao and Weikai Ren
Sensors 2025, 25(18), 5788; https://doi.org/10.3390/s25185788 - 17 Sep 2025
Viewed by 881
Abstract
Detecting dynamic and amorphous objects like fire and smoke poses significant challenges in object detection. To address this, we propose Dual-Path Cascade Stochastic DETR (Dual-Path CSDETR). Unlike Cascade DETR, our model introduces cascade stochastic attention (CSA) to model the irregular morphologies of fire [...] Read more.
Detecting dynamic and amorphous objects like fire and smoke poses significant challenges in object detection. To address this, we propose Dual-Path Cascade Stochastic DETR (Dual-Path CSDETR). Unlike Cascade DETR, our model introduces cascade stochastic attention (CSA) to model the irregular morphologies of fire and smoke through variational inference, combined with a dual-path architecture that enables bidirectional feature interaction for enhanced learning efficiency. By integrating object-centric priors from bounding boxes into each decoder layer, the model refines attention mechanisms to focus on critical regions. Experiments show that Dual-Path CSDETR achieves 94% AP50 on fire/smoke detection, surpassing deterministic baselines. Full article
(This article belongs to the Section Intelligent Sensors)
Show Figures

Figure 1

Back to TopTop