AI Paper Atlas

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

Enhancing Sound Source Localization via False Negative Elimination

Zengjie Song, Jiangshe Zhang, Yuxi Wang, Junsong Fan, Zhaoxiang Zhang

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization

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
add stop-gradient (ablation)SSPL from scratch · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.141 -> 0.570Improved
add ImageNet pre-training (ablation)SSPL with stop-gradient · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.570 -> 0.671Improved
add predictive coding module with 5 recursive cycles (ablation)SSPL w/o PCM · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.671 -> 0.743Improved
use 3 PCM cycles instead of 1 (ablation)SSPL w/ PCM · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.655 -> 0.719Improved
use min-max normalization instead of softmax scaling (ablation)SSPL attention module · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.667 -> 0.671Improved
use min-max normalization instead of ReLU scaling (ablation)SSPL attention module · SoundNet-Flickr (SSPL ablation, 10k)cIoU: 0.353 -> 0.671Improved
add fine-tuning of both backbones (ablation)SACL baseline · SoundNet-Flickr (SACL ablation, 10k)cIoU: 0.619 -> 0.707Improved
add pseudo masks (ablation)SACL fine-tuned · SoundNet-Flickr (SACL ablation, 10k)cIoU: 0.707 -> 0.755Improved
add false negative detection (ablation)SACL fine-tuned · SoundNet-Flickr (SACL ablation, 10k)cIoU: 0.707 -> 0.763Improved
add false negative detection on top of pseudo masks (ablation)SACL with pseudo mask · SoundNet-Flickr (SACL ablation, 10k)cIoU: 0.755 -> 0.815Improved
add PCM to SSPLSSPL w/o PCM · VGG-SS (trained on VGG-Sound144k)cIoU: 0.270 -> 0.339Improved
replace TIE with SACLTIE · VGG-SS (trained on VGG-Sound144k)cIoU: 0.386 -> 0.380Hurt

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