Follow
ViCrop: Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal Large Language Models. (arXiv:2310.16033v2 [cs.CV] UPDATED)
ViCrop: Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal Large Language Models. (arXiv:2310.16033v2 [cs.CV] UPDATED)