# AVPS-360: A Spatial Audio-Visual Benchmark for Instance Segmentation and Tracking of Sound-Producing Persons

**Authors:** Yifu Sun, Parthasaarathy Sudarsanam, Tuomas Virtanen, Archontis Politis  
**Lab:** Tampere University · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40480) · [PDF](https://arxiv.org/pdf/2610.40480) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40480.html)

## Key numbers

- **10.5**: it pairs first-order Ambisonics audio with synchronised 360° video across 230 recordings totalling 10.5 hours

## Abstract

Audio-visual instance segmentation (AVIS) segments and tracks individual sound-producing objects in videos. Existing benchmarks predominantly use monaural audio, which lacks inter-channel cues for spatially distinguishing concurrent sound sources. We introduce AVPS-360 (Audio-Visual Person Segmentation 360), a spatial audio-visual benchmark bridging AVIS and sound event localisation and detection (SELD). Built upon STARSS23, it pairs first-order Ambisonics audio with synchronised 360° video across 230 recordings totalling 10.5 hours. Recordings average 164.0 seconds. The dataset captures intermittent sound production in real-world interactions dominated by speech, alongside laughter, clapping, and footsteps. It provides 31,678 manually reviewed instance masks linked to source identities and sound-event labels. We also present a baseline that integrates spatial audio with visual features for frame-level segmentation and identity association across frames. Experiments on AVPS-360 show that existing AVIS methods struggle with detection and identity association in long recordings with intermittent sound production, while our baseline substantially improves performance in both aspects.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.