works on

From the 1 of 22 linked papers with an AI index.

activity
20242026
collaborators

22 papers

cs.CV2026

Non-Destructive Quantification of Urea Adulteration in Bovine Milk Using Transmittance Multispectral Imaging

Sharukshan Niranjan, Iresha Ranaweera, Tharindu Chandrarathne +5

Adulteration of bovine milk using urea remains a major food quality and health concern, motivating the development of rapid and quantitative screening tools. Conventional approache…

eess.SP2026

A Synchronized Multi-IMU Wearable System for Tracking of Joint-Angles in Sports Motion Analysis With Reference-Based Validation and Dynamic Task Characterization

Thevindu Samarasekera, Praveen Rathnayaka, Sachintha Adhikari +7

The paper introduces a low‑cost, synchronized multi‑IMU wearable platform and processing pipeline for accurately tracking joint angles during high‑dynamic sports movements, validat…

eess.IV2026

A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting

Oshadha Samarakoon, Dushan Herath, Ishara Ranmandala +4

Sky-image irradiance studies often compare forecasting systems in which the image encoder, temporal model, fusion block, target definition, and training recipe all change together.…

cs.AI2026

Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoning

Narthana Sivalingam, Santhirarajah Sivasthigan, Buddhi Wijenayake +3

Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions. Transformer-based approaches perform well but often rely on deep…

eess.IV2026

MambaRefine-CD: MambaVision with Region-Boundary Temporal Refinement

Dineth Perera, Thaariq Firdous, Oshadha Samarakoon +3

Binary change detection in remote sensing requires both complete changed-region localization and accurate boundary delineation. We present MambaRefine-CD, a region-boundary tempora…

cs.CV2026

ScaLe-INR: Scale and Learn Implicit Neural Representations

Buwaneka Epakanda, Athulya Ratnayake, Pandula Thennakoon +4

Implicit Neural Representations (INRs) parameterized by multilayer perceptrons excel at modeling continuous signals. However, a key challenge persists as INRs fundamentally suffer…