AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Audio-Visual Soundscape Stylization

Tingle Li, Renhao Wang, Po-Yao Huang, Andrew Owens, Gopala Krishna Anumanchipalli

ECCV 2024 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 3 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
add Gaussian noise to the enhanced input audio (ablation)audio-visual soundscape stylization model · CityWalkFAD: 2.66 -> 1.64Improved
condition on speech-containing audio instead of only separated sound effects (ablation)audio-visual soundscape stylization model · CityWalkRTE: 0.65 -> 0.20Improved
use two-stage enhancement (separation then enhancement) instead of separation only (ablation)audio-visual soundscape stylization model · CityWalkRTE: 0.60 -> 0.20Improved
use two-stage enhancement instead of enhancement-only or separation-only (ablation)enhancement strategy · CityWalkOVL: 3.221 -> 3.987Improved
keep matched audio-visual conditioning rather than randomly swapped audio or image (ablation)audio-visual soundscape stylization model · CityWalkFAD: 4.92 / 4.84 -> 1.64Improved
add visual conditioning to fine-tuned audio conditioning (ablation)audio-visual soundscape stylization model · CityWalkFAD: 2.08 -> 1.64Improved
add classifier-free guidance (ablation)audio-visual soundscape stylization model · CityWalkFAD: 3.37 -> 1.64Improved
fine-tune the CLAP audio encoder (ablation)audio conditioning · CityWalkFAD: 6.12 -> 2.08Improved
fine-tune the CLIP image encoder (ablation)visual conditioning · CityWalkFAD: 2.28 -> 2.29No clear effect
use pretrained CLIP and CLAP encoders instead of a ResNet-18 trained from scratch (ablation)audio-visual soundscape stylization model · CityWalkFAD: 2.41 -> 1.64Improved
do not normalize loudness of inputs (ablation)audio-visual soundscape stylization model · CityWalkFAD: 2.54 -> 1.64Improved
extend audio conditioning from 2.56s to 5.12s (ablation)audio-only conditioning · CityWalkFAD: 2.08 -> 2.10No clear effect

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