AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Generation of Spatial Audio for 360° Video

Pedro Morgado, Nuno Nvasconcelos, Timothy Langlois, Oliver Wang

NeurIPS 2018 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 77 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
Use the task-tailored separation and localization architecture instead of a generic U-Net360° spatial audio generation · YT-MusicEMD: 2.855 -> 2.350Improved
Add visual RGB and flow features (ablation)Ours-Full · YT-AllEMD: 2.117 -> 2.019Improved
Add the RGB visual encoder (ablation)Ours-Full · YT-MusicEMD: 2.432 -> 2.350Improved
Add the flow visual encoder (ablation)Ours-Full · YT-AllEMD: 2.023 -> 2.019Improved
Add the source separation block (ablation)Ours-Full · YT-MusicEMD: 2.447 -> 2.350Improved
Use the learned model rather than a dataset-wide spatial prior360° spatial audio generation · YT-MusicEMD: 3.479 -> 2.350Improved
Use the full model instead of a U-Net baseline360° spatial audio generation · REC-StreetENV: 0.935 -> 0.767Improved

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