Metraipolis › archive › dc_8cfa9def68c8
GLARE: Generating Listening Heads with Appropriate Reactions — arXiv:2609.40317
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40317
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:39.866Z
- SHA-256 of the archived text
c47d226f480fd09bb28be83c9008b15e4fe935dcd0c8370f1cde34237ebe3da9- Stable URL of this page
https://metraipolis.com/documento/dc_8cfa9def68c8
How to cite
GLARE: Generating Listening Heads with Appropriate Reactions — arXiv:2609.40317 — arXiv (en), https://arxiv.org/abs/2609.40317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cfa9def68c8 (Metraipolis archive dc_8cfa9def68c8, sha256 c47d226f480fd09bb28be83c9008b15e4fe935dcd0c8370f1cde34237ebe3da9)
BibTeX
@misc{dc8cfa9def68c8,
title = {GLARE: Generating Listening Heads with Appropriate Reactions — arXiv:2609.40317},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40317},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cfa9def68c8; sha256 c47d226f480fd09bb28be83c9008b15e4fe935dcd0c8370f1cde34237ebe3da9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While talking head generation has advanced rapidly, generating natural listener behavior in dyadic conversations, which know when to react, how to react, and with what type of response, remains underexplored. Existing dyadic datasets lack fine-grained listener reaction annotations, and prevailing evaluation metrics inherited from talking-head and video generation measure visual realism rather than whether a listener reacted appropriately. We address these gaps along three aspects. First, we curate a listening-head-specific dataset built from RealTalk and Seamless Interaction, comprising approximately 147 hours of paired speaker-listener videos with 64,557 event-level reaction annotations across six categories: nodding, head shaking, smiling, laughing, frowning, and surprised. Second, we introduce an audio-driven baseline built on a flow-matching transformer, namely GLARE, with prosody conditioning derived from Qwen2-Audio and a temporal reaction loss that explicitly supervises frame-wise reactions. Third, we propose a reaction-oriented evaluation protocol that jointly measures reaction occurrence (R-F1), temporal alignment (R-tIoU), asymmetric temporal deviation (R-ATD), and reaction-region visual quality (R-FID), giving a more behaviorally grounded assessment than visual-quality-only metrics. Experiment results show consistent gains over prior listening-head methods in both visual fidelity and reaction-level metrics, suggesting that reaction-aware data, modeling, and evaluation are critical for natural listening behavior. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.40317 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T14:19:00.859Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).