Participants are not allowed to modify the training procedure.

While supervised methods are effective, they require extensive labeled data for training. Recently, self-supervised foundation models have been introduced to these tasks showing comparable results to supervised methods.

Our dataset includes half a million design patents comprising 3.61 million figures along with captions from patents granted by the United States Patent and Trademark Office (USPTO) over a 16-year period from 2007 to 2022. We incorporate the metadata of each patent application with elaborate captions that are coherent with multiple viewpoints of designs.

Surgical video-language pretraining (VLP) faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data.

The word embedding space in neural models is skewed, and correcting this can improve task performance.