<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ali Torabi | Md. Mahbubur Rahman</title><link>https://mmrahman.pages.dev/authors/ali-torabi/</link><atom:link href="https://mmrahman.pages.dev/authors/ali-torabi/index.xml" rel="self" type="application/rss+xml"/><description>Ali Torabi</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 01 Sep 2026 00:00:00 +0000</lastBuildDate><item><title>Trait-Adaptive Hierarchical Attention Fusion of RGB-D data for automated lettuce phenotyping in hydroponic systems</title><link>https://mmrahman.pages.dev/publications/tahaf/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><guid>https://mmrahman.pages.dev/publications/tahaf/</guid><description>&lt;p&gt;Volume: 252; Pages: 112101; Article: 112101.&lt;/p&gt;
&lt;p&gt;The journal version is linked above. An earlier preprint used the title Task-Adaptive Hierarchical Attention Fusion.&lt;/p&gt;</description></item><item><title>Performance-optimized Alzheimer’s detection using machine learning with SMOTE and randomized hyperparameter tuning</title><link>https://mmrahman.pages.dev/publications/performance-optimized-alzheimer-s-detection-using-machine-learning-with-smote-and-randomized-hyperpa/</link><pubDate>Mon, 05 Jan 2026 00:00:00 +0000</pubDate><guid>https://mmrahman.pages.dev/publications/performance-optimized-alzheimer-s-detection-using-machine-learning-with-smote-and-randomized-hyperpa/</guid><description>&lt;p&gt;Volume: 6; Issue: 1; Article: 95.&lt;/p&gt;</description></item><item><title>Adaptive Correspondence Learning for Multi-View Fusion of 3D Gaussian Reconstructions for Non-Invasive Strawberry Plant Phenotyping</title><link>https://mmrahman.pages.dev/publications/adaptive-correspondence-learning-for-multi-view-fusion-of-3d-gaussian-reconstructions-for-non-invasi/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://mmrahman.pages.dev/publications/adaptive-correspondence-learning-for-multi-view-fusion-of-3d-gaussian-reconstructions-for-non-invasi/</guid><description>&lt;p&gt;This record links to the publicly available preprint.&lt;/p&gt;</description></item><item><title>Localized Region Guidance for Class Activation Mapping in WSSS</title><link>https://mmrahman.pages.dev/publications/localized-region-guidance-for-class-activation-mapping-in-wsss/</link><pubDate>Thu, 20 Nov 2025 00:00:00 +0000</pubDate><guid>https://mmrahman.pages.dev/publications/localized-region-guidance-for-class-activation-mapping-in-wsss/</guid><description>&lt;p&gt;This record links to the publicly available preprint.&lt;/p&gt;
&lt;p&gt;Version 2, revised 20 November 2025. Version 1 was titled Instance-Guided Class Activation Mapping for Weakly Supervised Semantic Segmentation.&lt;/p&gt;</description></item><item><title>Integrating deep CNN models for multilingual Sign Language recognition: A SignLink-based approach for Bengali and English</title><link>https://mmrahman.pages.dev/publications/integrating-deep-cnn-models-for-multilingual-sign-language-recognition-a-signlink-based-approach-for/</link><pubDate>Mon, 28 Jul 2025 00:00:00 +0000</pubDate><guid>https://mmrahman.pages.dev/publications/integrating-deep-cnn-models-for-multilingual-sign-language-recognition-a-signlink-based-approach-for/</guid><description>&lt;p&gt;This record links to the publicly available preprint.&lt;/p&gt;</description></item></channel></rss>