Papers › MAAS: Multi-modal Assignation for Active Speaker Detection

MAAS: Multi-modal Assignation for Active Speaker Detection

11 Jan 2021ICCV 2021 10arXiv:2101.03682archive 2025-07-28

Juan León-Alcázar, Fabian Caba Heilbron, Ali Thabet, Bernard Ghanem

Active speaker detection requires a solid integration of multi-modal cues. While individual modalities can approximate a solution, accurate predictions can only be achieved by explicitly fusing the audio and visual features and modeling their temporal progression. Despite its inherent muti-modal nature, current methods still focus on modeling and fusing short-term audiovisual features for individual speakers, often at frame level. In this paper we present a novel approach to active speaker detection that directly addresses the multi-modal nature of the problem, and provides a straightforward strategy where independent visual features from potential speakers in the scene are assigned to a previously detected speech event. Our experiments show that, an small graph data structure built from a single frame, allows to approximate an instantaneous audio-visual assignment problem. Moreover, the temporal extension of this initial graph achieves a new state-of-the-art on the AVA-ActiveSpeaker dataset with a mAP of 88.8\%.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fuankarion/maas officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Active Speaker DetectionAudio-Visual Active Speaker Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio-Visual Active Speaker Detection AVA-ActiveSpeaker MAAS-TAN validation mean average precision 88.8% #16 of 20 Archive leaderboard report
Audio-Visual Active Speaker Detection AVA-ActiveSpeaker MAAS-LAN validation mean average precision 85.1% #19 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections