AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers

Yutong Ban, Xavier Alameda-Pineda, Laurent Girin B, Radu Horaud

TPAMI 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Variational methods for sequence models · 56 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
use VAVIT instead of audio-visual baselines requiring simultaneous modalitiesaudio-visual tracking · AVDIAR living-room (FFOV)MOTA: 18.96 -> 96.03Improved
use VAVIT instead of the best baseline when the camera field of view is partialVAVIT · AVDIAR living-room (PFOV)MOTA: 66.39 -> 69.62Improved
use VAVIT instead of the best baseline when the camera field of view is partialVAVIT · AVDIAR meeting-room (PFOV)MOTA: 64.24 -> 65.27Improved
use VAVIT instead of the visual-only tracker with full field of viewVAVIT · AVDIAR living-room (FFOV)MOTA: 96.32 -> 96.03No clear effect
use VAVIT instead of the visual-only tracker with full field of viewVAVIT · AVDIAR meeting-room (FFOV)MOTA: 98.50 -> 98.16No clear effect
use VAVIT instead of the second-best baseline on AV16.3VAVIT · AV16.3MOTA: 82.9 -> 84.1Improved
add audio observations to visual tracking in the full field of viewVAVIT · AVDIAR (FFOV)OSPA-T: 14.79 -> 17.05Hurt
use VAVIT audio-visual tracking when persons leave the camera field of viewVAVIT · AVDIAR living-room (PFOV)MT: 45% -> 70%Improved
use VAVIT variational inference instead of particle-filter baseline in running timeVAVIT · AVDIAR living-roomcomputation time (s): 20821 -> 3456Improved
use VAVIT instead of visual-only OBVT in running timeVAVIT · AVDIAR living-roomcomputation time (s): 542 -> 3456Hurt
use VAVIT for diarization instead of audio-only DiarTKVAVIT · AVDIAR diarizationDER: 42.58 -> 28.73Improved
use VAVIT for diarization instead of the dedicated HMM audio-visual diarization methodVAVIT · AVDIAR diarizationDER: 18.88 -> 28.73Hurt

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