8 datasets found

Face aging techniques have used generative adversarial networks (GANs) and style transfer learning to transform one’s appearance to look younger/older. Identity is maintained by...

A high-resolution landscape video dataset with audio-visual pairs for sound-guided video generation task.

The VGGSound dataset is a large-scale audio-visual dataset containing 10,000 10-second video clips with corresponding audio files.

A dataset of audio-visual pairs where the audio is visually indicated.

A large-scale audio-visual dataset containing audio-visual pairs.

A novel framework for audio-guided local image stylization, named LISA. Audio-visual sound source localizer provides a delicate localization map by leveraging the CLIP embedding...

The CREMA-D dataset is an audio-visual dataset for emotion recognition task, each video in which consists of both facial and acoustic emotional expressions.

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature...