VGGSound

VGGSound VGG-Sound is an audio-visual correspondent dataset consisting of short clips of audio sounds, extracted from videos uploaded to YouTube. Homepage: https://www.robots.ox.ac.uk/~vgg/data/vggsound/ Paper: https://arxiv.org/abs/2004.14368 Github: https://github.com/hche11/VGGSound Analysis 310+ classes: VGG-Sound

Papers using VGGSound (7)

FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision2026DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap2025 · 2 citesGMS-CAVP: Improving Audio-Video Correspondence with Multi-Scale Contrastive and Generative Pretraining2026VGGSounder: Audio-Visual Evaluations for Foundation Models2025Training-free Multimodal Guidance For Video To Audio Generation2025ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities2023 · 42 citesMultimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models2022 · 9 cites