{"slug": "selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for", "title": "Selective Spatio-Temporal Fruit Inspector (S$^2$FI): A Mamba-based Framework for Rotational Fruit Quality Assessment", "summary": "Researchers developed the Selective Spatio-Temporal Fruit Inspector (S$^2$FI), a Mamba-based deep learning architecture that combines a 3D convolutional encoder with a Mamba backbone to sort fruit quality from rotational video, according to an arXiv paper (arXiv:2610.12868v1). The system uses a dual-conveyor and curved rail hardware design supporting household power and lightweight embedded deployment, and the team built a conveyor-based fruit quality video dataset of 6,460 samples. On the held-out test set, S$^2$FI outperformed compared baselines, which the authors report as the best trade-off among accuracy, efficiency, and practicality for small and medium-scale growers.", "body_md": "arXiv:2610.12868v1 Announce Type: new \nAbstract: The global fruit and vegetable industry confronts severe post-harvest sorting challenges for small and medium-scale growers. Large intelligent sorting systems are too costly, while manual sorting suffers from low efficiency, inconsistent standards, and high labor demand. To bridge this gap between expensive equipment and inefficient manual work, this study develops a low-cost, high-efficiency, lightweight fruit sorting system driven by deep learning, suitable for small and medium growers. We propose the Selective Spatio-Temporal Fruit Inspector (S$^2$FI) architecture, which combines a 3D convolutional encoder with a Mamba-based backbone.It efficiently extracts spatiotemporal features, adaptively weighs informative frames during fruit rotation, and models long-range dependencies with linear complexity, reducing motion blur and occlusion. The hardware uses a dual-conveyor and curved rail design, supporting household power, fast deployment, and lightweight embedded deployment to improve affordability. We also built a conveyor-based fruit quality video dataset with 6,460 samples. Experiments on the held-out test set show that our method achieves the best trade-off among accuracy, efficiency, and practicality, outperforming the compared baselines on the test set, achieving an excellent balance of accuracy, speed, and practicality for real-world sorting.", "url": "https://wpnews.pro/news/selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for", "canonical_source": "https://arxiv.org/abs/2610.12868", "published_at": "2026-10-12 04:00:00+00:00", "updated_at": "2026-10-12 04:42:50.823307+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "ai-research"], "entities": ["Selective Spatio-Temporal Fruit Inspector", "S$^2$FI", "Mamba", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for", "markdown": "https://wpnews.pro/news/selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for.md", "text": "https://wpnews.pro/news/selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for.txt", "jsonld": "https://wpnews.pro/news/selective-spatio-temporal-fruit-inspector-s-2-fi-a-mamba-based-framework-for.jsonld"}}