InfoQ

DoorDash Builds DashCLIP to Align Images, Text, and Queries for Semantic Search Using 32M Labels

DoorDash has launched a multimodal machine learning system that aligns product images, text, and user queries in a shared ...
Frontiers

DenseLes: slice-wise dense network for multiple sclerosis lesion segmentation and classification

Accurate and reliable segmentation of multiple sclerosis (MS) lesions from magnetic resonance imaging (MRI) is essential for diagnosis and monitoring disease progression. Therefore, a robust and ...
IEEE

HiGATA: Hierarchy-aware Graph Attention Networks Enhanced by Topological Analysis for Hierarchical Multi-Label Text Classification

Abstract: Hierarchical text classification (HTC) is an important yet challenging task in natural language processing (NLP), primarily due to the complexity of its taxonomic label hierarchy. Existing ...
IEEE

Multi-Label Image Classification Based on Higher-Order Semantic Awareness Encoding

Abstract: Multi-label classification (MLC) tasks aim at assigning multiple labels to each sample and are widely used to deal with scenarios where the sample contains multiple objects or concepts.