AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning to Separate Object Sounds by Watching Unlabeled Video

Ruohan Gao, Rogerio Feris, Kristen Grauman

ECCV 2018 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 267 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
use learned object-specific audio bases instead of bases from a single exemplar video (ablation)supervised NMF source separation · AudioSet instrument pairsSDR (dB): -2.41 -> 1.83Improved
retrieve bases of the correct visually detected class instead of random wrong-class bases (ablation)supervised NMF source separation · AudioSet instrument pairsSDR (dB): -2.12 -> 1.83Improved
use learned bases instead of random Gaussian bases (ablation)supervised NMF source separation · AudioSet instrument pairsSDR (dB): -8.74 -> 1.83Improved
use learned bases instead of random Gaussian bases (ablation)supervised NMF source separation · AudioSet cross-domain pairsSDR (dB): -8.21 -> 2.53Improved
use visually guided object bases instead of K-means clustering of NMF channels (ablation)unsupervised NMF separation · AudioSet animal pairsSDR (dB): -3.76 -> 0.23Improved
use visually guided object bases instead of MFCC unsupervised separationunsupervised separation · AudioSet instrument pairsSDR (dB): 0.47 -> 1.83Improved
train with ground-truth AudioSet labels instead of ImageNet-CNN weak labels (ablation)deep MIML network · AudioSet instrument pairsSDR (dB): 1.83 -> 2.05Improved
use ImageNet ResNet-152 weak labels instead of ground-truth labels (ablation)deep MIML network · AudioSet pairsSDR (dB)No clear effect
replace Pu et al. with the proposed method for denoisingAV-Bench denoising · AV-Bench denoising (Wooden Horse)NSDR (dB): 8.82 -> 12.3Improved
replace Pu et al. with the proposed method for denoisingAV-Bench denoising · AV-Bench denoising (Guitar Solo)NSDR (dB): 14.1 -> 11.4Hurt
replace Pu et al. with the proposed method for denoisingAV-Bench denoising · AV-Bench denoising (average)NSDR (dB): 9.61 -> 10.5Improved

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