[CVPR 2019] "Handwriting Recognition in Low-resource Scripts using Adversarial Learning ”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2019.

Create handwritten word embeddings from a text recognition Seq2Seq system.

Small footprint, standalone, zero dependency, offline keyword spotting (KWS) CLI tool.

Additional support for three datasets: Botany, Konzilsprotokolle and Esposalles for the Ctrl-F-Mini Network.

🛡️ Explore visual prompt injection risks in AI browsers by uncovering hidden commands in images and layouts, enhancing security against multimodal threats.