4 papers
Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
Zilin Du, Haoxin Li, Jianfei Yu +1
Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grou…
Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
Haoxin Li, Boyang Li
Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with prop…
Learning to Animate Images from A Few Videos to Portray Delicate Human Actions
Haoxin Li, Yingchen Yu, Qilong Wu +3
Despite recent progress, video generative models still struggle to animate static images into videos that portray delicate human actions, particularly when handling uncommon or nov…
Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA
Miaoyu Li, Haoxin Li, Zilin Du +1
Knowledge-based Visual Question-answering (K-VQA) often requires the use of background knowledge beyond the image. However, we discover that a single knowledge generation strategy…