Introduces AtomLenz, an OCSR tool that combines object detection with a molecular graph constructor. Features a novel weakly supervised training scheme (ProbKT*) to learn atom-level localization from SMILES-only data, achieving state-of-the-art results on hand-drawn images.
MolScribe reformulates molecular recognition as an image-to-graph generation task, explicitly predicting atom coordinates and bonds to better handle stereochemistry and abbreviated structures compared to image-to-SMILES baselines.
A three-level grammatical framework (formula, molecule, text) for parsing online handwritten chemical formulas, generating semantic graphs that capture both connectivity and layout using context-free grammars and HMMs.
MolNexTR proposes a dual-stream architecture combining ConvNext and Vision Transformers to improve molecular image recognition (OCSR). It achieves 81-97% accuracy across diverse benchmarks utilizing simultaneous local and global feature extraction alongside specialized image contamination augmentations.
A foundational 1931 paper that derives exact recursive formulas for counting alkane structural isomers, correcting historical errors and establishing the first systematic enumeration up to C₄₀.