Search Results for author:
Found 4 papers, 1 papers with code
Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track
Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to improve the data quality.
Role-Aware Interaction Generation from Textual Description
We claim that certain interactions, which we call asymmetric interactions, involve a relationship between an actor and a receiver, whose motions significantly differ depending on the assigned role.
Captioning Images with Novel Objects via Online Vocabulary Expansion
In this study, we introduce a low cost method for generating descriptions from images containing novel objects.
Generating Easy-to-Understand Referring Expressions for Target Identifications
Moreover, we regard that sentences that are easily understood are those that are comprehended correctly and quickly by humans.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
