AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Learning of Audio-Visual Objects from Video

Triantafyllos Afouras, Andrew Owens, Joon Son Chung, Andrew Zisserman

ECCV 2020 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 233 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 optical-flow aggregation of attention over time (ablation)audio-visual object model · Talking head detection (LRS3)detection accuracy: 94.2% -> 99.7%Improved
add optical-flow aggregation of attention over time (ablation)audio-visual object model · Talking head detection (LRS2)detection accuracy: 98.4% -> 99.6%Improved
enlarge NMS window to rho=150 in no-flow model (ablation)no-flow variant · Talking head detection (LRS3)detection accuracy: 94.2% -> 97.2%Improved
add flow on high-motion videos (ablation)audio-visual object model · Talking head detection (LRS3-test high motion)detection accuracy: 88.1% -> 99.3%Improved
add flow on high-motion videos (ablation)audio-visual object model · Talking head detection (LRS2-val high motion)detection accuracy: 93.6% -> 96.1%Improved
end-to-end training instead of frozen pretrained features (ablation)source separation · LRS2 (3 speakers)SDR: 7.0 -> 7.2Improved
use rho=150 instead of rho=100 (ablation)source separation · LRS2 (3 speakers)WER %: 44.7 -> 42.0Improved
use face-detector tracks instead of audio-visual objects (ablation)source separation · LRS2 (3 speakers)WER %: 44.9 -> 42.0No clear effect
replace supervised face detection with self-supervised objectssource separation · LRS2 (2 speakers)SDR: 11.3 -> 10.8Hurt
use self-supervised object embeddings instead of SyncNetactive speaker detection · Columbiaaverage F1: 89.5 -> 90.8Improved
use self-supervised objects instead of Perfect Match supervisedsynchronization · LRS2 (5 input frames)accuracy: 88.1 -> 78.8Hurt
use self-supervised model instead of RetinaFace MobileNetnon-human speaker localization · Simpsons single-headlocalization accuracy: 72.1 -> 98.8Improved

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