# STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization

arXiv: https://arxiv.org/abs/2306.10608 · HTML: https://mlsanity.com/paper/2306.10608/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 18 Jun 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection](https://mlsanity.com/paper/2107.06592/) (2021)
- [Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection](https://mlsanity.com/paper/2207.07783/) (2022)
- [AVA-AVD: Audio-Visual Speaker Diarization in the Wild](https://mlsanity.com/paper/2111.14448/) (2021)
- [Who said that?: Audio-visual speaker diarisation of real-world meetings](https://mlsanity.com/paper/1906.10042/) (2019)
- [Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization](https://mlsanity.com/paper/2210.07764/) (2022)
- [Using Active Speaker Faces for Diarization in TV shows](https://mlsanity.com/paper/2203.15961/) (2022)

## Built on by (most cited first, 6 of 6)

- [Action Scene Graphs for Long-Form Understanding of Egocentric Videos](https://mlsanity.com/paper/2312.03391/) (2023)
- [VideoSAGE: Video Summarization with Graph Representation Learning](https://mlsanity.com/paper/2404.10539/) (2024)
- [GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection](https://mlsanity.com/paper/2512.15707/) (2025)
- [Graph-Based Multimodal and Multi-view Alignment for Keystep Recognition](https://mlsanity.com/paper/2501.04121/) (2025)
- [Keystep Recognition using Graph Neural Networks](https://mlsanity.com/paper/2506.01102/) (2025)
- [EgoVIS@CVPR: PAIR-Net: Enhancing Egocentric Speaker Detection via Pretrained Audio-Visual Fusion and Alignment Loss](https://mlsanity.com/paper/2506.02247/) (2025)

## Abstract (arXiv)

This report introduces our novel method named STHG for the Audio-Visual Diarization task of the Ego4D Challenge 2023. Our key innovation is that we model all the speakers in a video using a single, unified heterogeneous graph learning framework. Unlike previous approaches that require a separate component solely for the camera wearer, STHG can jointly detect the speech activities of all people including the camera wearer. Our final method obtains 61.1% DER on the test set of Ego4D, which significantly outperforms all the baselines as well as last year's winner. Our submission achieved 1st place in the Ego4D Challenge 2023. We additionally demonstrate that applying the off-the-shelf speech recognition system to the diarized speech segments by STHG produces a competitive performance on the Speech Transcription task of this challenge.