← Search

David Yang

4 accepted papers

2025

CompCap: Improving Multimodal Large Language Models with Composite Captions

ICCV 2025poster

How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured directly by a camera. While CIs are prevalent in real-world…

2022

Object-Centric Unsupervised Image Captioning

ECCV 2022poster

"Image captioning is a longstanding problem in the field of computer vision and natural language processing. To date, researchers have produced impressive state-of-the-art performance in the age of deep learning. Most of these state-of-the-art, however, requires large volume of annotated image-capti…