work EmbodiedMAE Multi-modal Masked Autoencoder for 3D Plant Phenotyping Lighting-Robust Instance Segmentation SAM extended with a Lighting Convolutional Attention module Seizure Video–EEG Synchronisation Multimodal EEG + video pipeline for seizure data-distribution analysis AFM Contact Mode Simulator Browser-based simulator of AFM tip-geometry artifacts via Minkowski-sum morphology ICDAR 2025 HNU Challenge Handwritten Notes Understanding competition benchmark Doc2GraphFormer Bridging graph learning with transformer attention for document understanding Tricho-Vision Computer vision for trichotaxonomy and wildlife conservation NoTeS-Bank Benchmarking Neural Transcription and Search for scientific notes Doc2Graph-X A multilingual graph-based framework for form understanding FASTER Font-Agnostic Scene Text Editing and Rendering Framework FastTextSpotter High-Efficiency Transformer for Multilingual Scene Text Spotting DA-TextSpotter Domain-agnostic scene text spotting in multi-domain noisy scenes Swin-TESTR Multi-lingual pre-training for domain-adaptive text spotting
