GraSP introduces a general framework for recognizing graphs in images by framing it as sequential subgraph prediction with a binary classifier. A GNN conditions a CNN via FiLM layers to predict whether a candidate graph is a subgraph of the target. Applied to OCSR on QM9, GraSP achieves 67.5% accuracy with no domain-specific modifications.
Battaglia et al. argue that combinatorial generalization requires structured representations, systematically analyze the relational inductive biases in standard deep learning architectures (MLPs, CNNs, RNNs), and present the graph network as a unifying framework that generalizes and extends prior graph neural network approaches.
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.