AI Paper Atlas

Research map / Benchmarks / VGGSound

VGGSound leaderboard

26 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VGGSound. Best accuracy: 97.22 (Frieren, NeurIPS 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VGGSound · accuracy

16 papers, each with its best reported number for its own method; higher is better.

6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

VGGSound · FAD

11 papers, each with its best reported number for its own method; lower is better.

#FAD ↓MethodPaperTopic
10.4MGAudio, CFG = 1.45Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
NeurIPS 2025 · Table: MGAudio on VGGSound
Video generation
20.52Foley-FlowFoley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows
CVPR 2025 · Table 1
Video generation
30.841V2A-Mapper
CLIP + CLAP + AudioLDM
V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models
AAAI 2024 · Table 1
Cross-modal learning
40.94TARO
MMDiT flow transformer
TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
ICCV 2025 · Table 1
Video generation
51.32FrierenFrieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching
NeurIPS 2024 · Table 1
Video generation
61.51MaskVAT Seq2Seq
DAC
Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity
ECCV 2024 · Table 1
Video generation
71.59HarmoniDPO (aligned + DDS)
Tango-2
HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
IJCV 2026 · Table 1
Video generation
82.16ReWaS
AudioLDM-M
Read, Watch and Scream! Sound Generation from Text and Video
AAAI 2025 · Table 1
Video generation
92.161MDSGen-B with HiFi-GANMDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation
ICLR 2025 · Table: FAD on VGGSound test se
Video generation
102.35VATT-Gemma
Gemma-2B
Tell What You Hear From What You See - Video to Audio Generation Through Text
NeurIPS 2024 · Table: Quantitative results ag
Video generation
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.