AI Paper Atlas

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

MAAS: Multi-Modal Assignation for Active Speaker Detection

Juan Léon Alcázar, Fabian Caba, Ali K. Thabet, Bernard Ghanem

ICCV 2021 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 57 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 static graph stream to dynamic stream (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 66.5 -> 88.8Improved
add dynamic graph stream to static stream (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 87.9 -> 88.8Improved
increase GCN depth from 1 to 4 layers (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.0 -> 88.8Improved
increase GCN depth from 4 to 5 layers (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.8 -> 87.5Hurt
increase filters from 64 to 256 (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.8 -> 88.1Hurt
increase filters from 32 to 64 (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.5 -> 88.8Improved
use K=3 instead of K=2 neighbors (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.5 -> 88.8Improved
use K=3 instead of K=5 neighbors (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.4 -> 88.8Improved
extend from 1 LAN to 13 LANs (temporal graph) with 4 video nodes (ablation)MAAS · AVA-ActiveSpeaker valmAP: 85.1 -> 88.8Improved
increase LANs from 13 to 15 (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.8 -> 88.5Hurt
increase video nodes per LAN from 1 to 4 with 1 LAN (ablation)MAAS · AVA-ActiveSpeaker valmAP: 80.2 -> 85.1Improved
add supervision on audio nodes (ablation)MAAS-TAN · AVA-ActiveSpeaker valmAP: 88.5 -> 88.8Improved

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