Cordelia Schmid

Research shows how domain randomization aids robots in real-world tasks.

A new approach enhances video localization tasks using pretrained models.

A fresh method improves video quality while reducing resource use.

SceneCraft creates 3D scenes from text, making design easier and more efficient.

A new framework improves image recognition accuracy and efficiency for web entities.

This article discusses using image captions to find videos efficiently.

This article examines how Machine Learning estimates treatment effects in ant behavior studies.

mOSCAR provides a multilingual dataset for improved AI understanding of text and images.

ZeroMMT uses monolingual multimodal data to enhance translation without expensive datasets.

Advancements in image processing are transforming how computers understand visual content.