الملخص
We present a method for learning binaural sound localization using egomotion as a supervisory signal. Over the course of a video, the cameras direction to a sound source will change as the camera moves. We train an audio model to predict sound directions that are consistent with visual estimates of camera motion, which we obtain using traditional methods from multi-view geometry. This provides a weak but plentiful form of supervision that we combine with traditional binaural cues. To evaluate this method, we propose a dataset of real-world audio-visual videos with egomotion. We show that our model can successfully learn from real-world data and that it performs well on sound localization tasks
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Min, A., Chen, Z., Zhao, H., & Owens, A. (2026). Supervising Sound Localization by In-the-wild Egomotion. https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion
MLA 9
Min, Anna, et al. "Supervising Sound Localization by In-the-wild Egomotion." https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion.
شيكاغو (المؤلف–التاريخ)
Min, Anna, Ziyang Chen, Hang Zhao, and Andrew Owens. 2026. "Supervising Sound Localization by In-the-wild Egomotion." https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion.
هارفارد
Min, A., Chen, Z., Zhao, H. and Owens, A. (2026) 'Supervising Sound Localization by In-the-wild Egomotion', Available at: https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion.
فانكوفر
Min A, Chen Z, Zhao H, Owens A. Supervising Sound Localization by In-the-wild Egomotion. https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion
IEEE
A. Min, Z. Chen, H. Zhao, and A. Owens, "Supervising Sound Localization by In-the-wild Egomotion," https://omanscience.com/ar/articles/supervising-sound-localization-by-in-the-wild-egomotion.