AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Binaural SoundNet: Predicting Semantics, Depth and Motion With Binaural Sounds

Dengxin Dai, Arun Balajee Vasudevan, Jiří Matas, Luc Van Gool

TPAMI 2022 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 10 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 binaural instead of mono audioSpectrogram encoder · Auditory semantic prediction (spectrogram, manual test)mIoU (%): 21.14 -> 28.02Improved
add S3R auxiliary task (ablation)Ours(B) · Auditory semantic prediction (spectrogram, manual test)mIoU (%): 28.02 -> 37.80Improved
add depth auxiliary task (ablation)Ours(B) · Auditory semantic prediction (spectrogram, manual test)mIoU (%): 28.02 -> 36.11Improved
add motion auxiliary task (ablation)Ours(B) · Auditory semantic prediction (spectrogram, manual test)mIoU (%): 28.02 -> 35.12Improved
add all three auxiliary tasks (S3R, depth, motion) (ablation)Ours(B) · Auditory semantic prediction (spectrogram, manual test)mIoU (%): 28.02 -> 38.27Improved
add all three auxiliary tasks (ablation)Ours(B), DDSP encoder · Auditory semantic prediction (DDSP, manual test)mIoU (%): 20.67 -> 25.44Improved
add all three auxiliary tasks (ablation)Ours(B), spectrogram + DDSP encoder · Auditory semantic prediction (spectrogram + DDSP, manual test)mIoU (%): 32.27 -> 42.16Improved
add ASPP module to audio encoder (ablation)Mono audio encoder · Auditory semantic predictionmIoU: 13.21 to 22.12Improved
increase input channels from mono to all 8 microphonesOurs(B) · Auditory semantic predictionmIoU (%): 22.12% -> 40.32%Improved
add auxiliary tasks (semantic, depth, motion) (ablation)Binaural depth model, spectrogram · Auditory depth predictionAbs Rel: 108.59 -> 83.22Improved
add auxiliary tasks (S3R, semantic, depth) (ablation)Binaural motion model, spectrogram · Auditory motion predictionEPE: 16.22 -> 14.04Improved
add semantic, depth and motion tasks to S3R (ablation)S3R, spectrogram · Spatial sound super-resolutionMSE-1: 0.1228 -> 0.0940Improved

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