AI Paper Atlas

Research map / Video / Video segmentation and tracking

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

Kazuki Shimada, Archontis Politis, Parthasaarathy Sudarsanam, Daniel Aleksander Krause, Kengo Uchida, Sharath Adavanne, Aapo Hakala, Yuichiro Koyama, Naoya Takahashi, Shusuke Takahashi, Tuomas Virtanen, Yuki Mitsufuji

NeurIPS 2023 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 13 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 visual person bounding-box embedding to audio-only SELD (13 classes, FOA)CRNN multi-ACCDOA SELD · STARSS23 dev-set-test 13 classes FOAF-score 20deg: 14.8 -> 13.2Hurt
add visual person bounding-box embedding (13 classes, FOA)CRNN multi-ACCDOA SELD · STARSS23 dev-set-test 13 classes FOAlocalization error: 55.9 -> 51.6Improved
add visual person bounding-box embedding (13 classes, MIC)CRNN multi-ACCDOA SELD · STARSS23 dev-set-test 13 classes MIClocalization error: 66.9 -> 60.0Improved
add visual person bounding-box embedding (13 classes, MIC)CRNN multi-ACCDOA SELD · STARSS23 dev-set-test 13 classes MICF-score 20deg: 10.7 -> 10.0No clear effect
add visual person bounding-box embedding on body-related classes only (FOA)CRNN multi-ACCDOA SELD · STARSS23 5 body-related classes FOAF-score 20deg: 18.0 -> 22.4Improved
add visual person bounding-box embedding on body-related classes only (MIC)CRNN multi-ACCDOA SELD · STARSS23 5 body-related classes MICF-score 20deg: 16.0 -> 20.9Improved
add visual person bounding-box embedding on body-related classes only (MIC)CRNN multi-ACCDOA SELD · STARSS23 5 body-related classes MIClocalization error: 58.4 -> 28.9Improved
add person-box visual input, evaluated on non-body-related classesCRNN multi-ACCDOA SELD · STARSS23 13 classes FOA, non-body classesF-score 20degHurt
use CNN-based visual features instead of object-detector bounding boxes (ablation)audio-visual SELD · STARSS23SELD performanceHurt
use FOA instead of MIC audio formatSELD systems · STARSS23 dev-set-test 13 classesF-score 20deg: 10.0 -> 13.2 (audio-visual)Improved

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