Vggsound T2Av: Audio-Video Prompts for Joint Denoising Research

Metadata for the VGGSound dataset, annotated with video and audio prompts for the paper "Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation". The dataset was created by author jianzongwu and the metadata was last updated on December 3, 2025. The repository contains annotated train and evaluation metadata, while the video files must be downloaded from a separate source.

Use Cases

• Training audio-conditioned video generation models based on the provided audio prompts.
• Evaluating joint audio-video denoising methods based on the annotated metadata.
• Researching cross-modal learning for video synthesis based on the paired audio-video prompts.

Strengths

• Metadata is specifically annotated for a published research paper on audio-video joint denoising.
• Last updated on 2025-12-03, indicating recent maintenance.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Annotated metadata derived from the VGGSound dataset.

Freshness

Last updated 2025-12-03 02:13:28