AI Paper Atlas

Research map / Video / Video segmentation and tracking

Ambient Sound Provides Supervision for Visual Learning

Andrew Owens, Jiajun Wu, Josh H. McDermott, William T. Freeman, Antonio Torralba

ECCV 2016 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 391 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
predict sound texture statistics instead of only the instantaneous frequency spectrum (ablation)Sound (binary) · PASCAL VOC 2007 classification (pool5)mAP (%): 44.0 -> 46.7Improved
use sound labels instead of visual texton histogram labels (ablation)Sound (cluster) · PASCAL VOC 2007 classification (pool5)mAP (%): 37.5 -> 45.8Improved
use sound labels instead of visual texton histogram labels (ablation)Sound (cluster) · SUN397 (pool5)accuracy (%): 15.2 -> 22.9Improved
use binary coding labels instead of clustering labels (ablation)Sound · PASCAL VOC 2007 classification (pool5) fc7mAP (%): 44.3 -> 47.4Improved
increase number of audio clusters (ablation)Sound (cluster) · PASCAL VOC 2007 classification (pool5)mAP (%)Improved
use global max pooling of conv5 features (max5) in place of other layers (ablation)Sound (binary) · PASCAL VOC 2007 classificationmAP (%): 39.4 vs 46.7 (pool5)Mixed
add sound-pretrained initialization before Fast R-CNN finetuning (ablation)Sound (cluster) · PASCAL VOC 2007 detectionmAP (%): 41.3 -> 44.1Improved
use sound supervision instead of tracking supervision (ablation)Sound (cluster) · PASCAL VOC 2007 detectionmAP (%): 44.1 vs 47.4No clear effect
use sound supervision instead of egomotion supervisionSound (cluster) · PASCAL VOC 2007 classification (pool5)mAP (%): 31.1 -> 45.8Improved
train on ambient sound instead of human scene labelsSound (cluster) · Object-selective unitsnumber of detectors for objects with characteristic sounds: 26 -> 49Improved

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