MainReads

Discover Books. Explore Knowledge.

Home » Academic Articles & Research Papers

Academic Articles & Research Papers

Search and discover peer-reviewed scholarly literature, open-access articles, and research citations across DOAJ, PubMed Central, and OpenAlex.

Reset
Showing 4 of 4 academic articles

ProtoMix: Unified Prototype Learning for Semantic Change Detection in Remote Sensing

Hengzhi Chen, Kun Hu, Patrick Filippi, Wei Xiang et al. • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2026)

As an emerging topic, semantic change detection (SCD) in remote sensing aims to both identify the locations of changes before and after events and determine the land cover (LC) classes of changed regions. While deep learning has demonstrate...

DOAJ Open Access (DOAJ) DOI: 10.1109/JSTARS.2026.3715175

Multitask Learning Mechanism for Remote Sensing Image Motion Deblurring

Jie Fang, Xiaoqian Cao, Dianwei Wang, Shengjun Xu • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2021)

As a fundamental preprocessing technique, remote sensing image motion deblurring is important for visual understanding tasks. Most conventional approaches formulate the image motion deblurring task as a kernel estimation. Because the kernel...

DOAJ Open Access (DOAJ) DOI: 10.1109/JSTARS.2020.3047636

A unified architecture for natural language processing

Ronan Collobert, Jason Weston • International Conference on Machine Learning (2008)

We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the lik...

OPENALEX DOI: https://doi.org/10.1145/1390156.1390177

Availability-Aware Multitask Learning for Robust Clinical Prediction from Incomplete Electronic Health Records

Zhainagul Khamitova, Gulmira Omarova, Akerke Akanova, Aliya Abdukarimova et al. • Computers (2026)

This study presents NORIA, an availability-aware multitask learning framework for clinical prediction from incomplete electronic health records (EHRs). We analyzed a public dataset of 77,724 patients and 107 numerical features. To prevent t...

DOAJ Open Access (DOAJ) DOI: 10.3390/computers15100723