Chunhui Lin

scene text recognition (2) benchmark evaluation (1) few-shot learning (1) domain adaptation (1) visual question answering (1) in-context learning (1) multimodal learning (1) image captioning (1) modality alignment (1) visual recognition (1) parallel processing (1) low-rank adaptation (1) multimodal large language model (1) visual text generation (1) multilingual benchmark (1) multimodal generative model (1) text-centric scene understanding (1) human expert annotation (1) layout analysis (1) human performance (1)