Yapeng Tian

Peanut streamlines audio-visual data labeling, enhancing speed and accuracy.

DiffI2I enhances image-to-image translation with improved accuracy and efficiency.

DAVIS offers a fresh way to tackle audio and visual sound separation.

Spica enhances video access for blind and low-vision users through interactivity.

Mimosa simplifies spatial audio creation for amateur video makers.

AV-DiT offers a new way to generate synchronized audio and video efficiently.

A new AR system enhancing kitchen safety for individuals with low vision.

SaSR-Net connects sounds and visuals to accurately answer questions about videos.

Study enhances video understanding through motion-focused questions and visual answers.