AI Paper Atlas

Research map / Video / Video generation

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

Thomas Hayes, Songyang Zhang, Xi Yin, Guan Pang, Sasha Sheng, Harry Yang, Songwei Ge, Qiyuan Hu, Devi Parikh

ECCV 2022 · Video › Video generation · approach: Video-to-audio synthesis · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
query with video-retrieval A+T ensemble instead of audio alonevideo retrieval · MUGEN video retrievalRecall@1: 58.59 -> 81.50Improved
use ensemble of separate models instead of joint model (A+T*)video retrieval · MUGEN video retrievalRecall@1: 62.54 -> 81.50Improved
use ensemble of separate models instead of joint model (V+T*)audio retrieval · MUGEN audio retrievalRecall@1: 41.83 -> 69.59Improved
add video query to text query for audio retrievalaudio retrieval · MUGEN audio retrievalRecall@1: 2.40 -> 69.59Improved
raise video frame rate from 8 to 32 framesT2V generation · MUGEN T2V (full train)FVD: 112.7 -> 61.0Improved
raise video frame rate from 8 to 32 framesV2T generation · MUGEN V2TR.Sim.: 83.5 -> 108.0Improved
use auto-text instead of manual textT2V generation · MUGEN T2V (full train)FVD: 61.0 -> 140.7Hurt
add auto-text to manual textT2V generation · MUGEN T2V (full train)FVD: 61.0 -> 61.4No clear effect
train on down-sampled balanced set instead of full setT2V generation · MUGEN T2VR.Sim.: 64.9 -> 70.6Improved
lower audio compression (more tokens, 68 to 551)A2T generation · MUGEN A2TCIDEr: 14.1 -> 15.5Improved
lower audio compression (more tokens) 68 to 551V2A generation · MUGEN V2AFAD: 523.8 -> 50.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy