AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Look, Listen and Learn

Relja Arandjelovic, Andrew Zisserman

ICCV 2017 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 865 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 AVC (L3) self-supervised training to the audio network (ablation)L3-Net audio subnetwork · ESC-50accuracy (%): 62.5 -> 79.3Improved
add AVC (L3) self-supervised training to the audio network (ablation)L3-Net audio subnetwork · DCASEaccuracy (%): 85 -> 93Improved
add AVC (L3) self-supervised training to the vision network (ablation)L3-Net vision subnetwork · ImageNet linear classificationtop-1 accuracy (%): 12.9 -> 32.3Improved
add AVC training to the vision network (ablation)L3-Net vision subnetwork · Kinetics-Sounds clusteringNMI (vision): 0.204 -> 0.409Improved
add AVC training to the audio network (ablation)L3-Net audio subnetwork · Kinetics-Sounds clusteringNMI (audio): 0.219 -> 0.330Improved
train both vision and audio networks instead of using fixed supervised teacher vision nets (SoundNet)audio representation · ESC-50accuracy (%): 74.2 -> 79.3Improved
train both vision and audio networks instead of using fixed supervised teacher vision nets (SoundNet)audio representation · DCASEaccuracy (%): 88 -> 93Improved
replace direct combination of supervised class scores with training the fusion layers on AVCsupervised baselines · Kinetics-Sounds AVCAVC test accuracy (%): 65 -> 74Improved
replace supervised pretrained features with self-supervised L3 featuresAVC fusion network · Kinetics-Sounds AVCAVC test accuracy (%): 74 -> 74No clear effect
use L3-Net vision features instead of the earlier best self-supervised AlexNet featuresImageNet linear classification · ImageNet linear classificationtop-1 accuracy (%): 34.7 -> 32.3Hurt

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