First-of-its-kind automated root imaging platform speeds plant discoveries

The Department of Energy's Oak Ridge National Laboratory has launched a novel robotic platform to rapidly analyze plant root systems as they grow, yielding AI-ready data to accelerate the development ...
IEEE

Enhancing Image-Based JPEG Compression: ML-Driven Quantization via DCT Feature Clustering

Abstract: JPEG compression is a widely used technique for reducing the file size of digital images, but it often compromises visual quality. The purpose of this research is to explore a novel approach ...
GitHub

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

2014_IEEE Multimedia_PRVQ_Projected residual vector quantization for ANN search. [IEEE] 2015_arXiv_IRVQ_Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search. ...
IEEE

Multi-Resolution Infrared-Visible Image Fusion using Multi-Scale Residual Quantization

Infrared-visible image fusion (IVF) is an essential task in multimodal image processing that integrates infrared and visible modalities to enhance the overall image information content. However, ...
GitHub

Boltzmann Attention Sampling for Image Analysis with Small Objects

BoltzFormer is designed for text promptable segmentation, with superior performance for small objects. It performs Boltzmann sampling within the attention mechanism in the transformer, allowing the ...