Multiscale attention guided historical prompt tracking for industrial particles

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Industrial particle tracking during discharge and transport is challenging because particles are often small, visually similar, densely packed, frequently occluded, and subject to rapid motion, all of which can cause tracking drift. To address these challenges, this paper proposes MSA-HPTrack, a Multi-Scale Attention-Guided Historical Prompt Tracking network for industrial particle tracking. Built upon the HIPTrack framework, the proposed method addresses two key limitations: the dilution of small-target responses caused by average pooling in historical prompt encoding, and the sensitivity of single-scale Key–Query representations in historical memory retrieval to scale variations and local disturbances. First, an attention-guided spatial pooling mechanism is introduced into the historical prompt encoder. It replaces global average pooling with attention-weighted aggregation and jointly models the result with max pooling, thereby enhancing target-relevant responses and reducing interference from dense backgrounds and neighboring particles during historical feature encoding. Second, a multi-scale adaptive Key–Query enhancement module is incorporated into the historical prompt decoder. By exploiting $$1 \times 1$$ , $$2 \times 2$$ , and $$4 \times 4$$ pooling scales, the module captures global, regional, and local contextual information while preserving the original feature dimensionality, allowing the original L2-distance-based memory matching and prompt retrieval process to remain unchanged. Experimental results show that MSA-HPTrack maintains competitive general tracking performance while providing improved robustness in industrial small-particle scenarios,particularly under small target size, dense occlusion, high appearance similarity,rapid motion, and background interference.