AI Paper Atlas

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

Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser

Yung-Hsuan Lai, Yen-Chun Chen, Yu-Chiang Frank Wang

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 3 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 HAN as dense labeler instead of CLIP and CLAP (ablation)Valor · AVVP LLP valsegment Type@AV: 63.4 -> 56.8Hurt
modality-agnostic segment labels instead of modality-aware (ablation)Valor · AVVP LLP valsegment Type@AV: 63.4 -> 44.9Hurt
replace video-level labels by refined labels in global loss (ablation)HAN baseline · AVVP LLP valsegment Type@AV: 54.0 -> 60.8Improved
add CLIP/CLAP segment-level dense labels (ablation)Valor · AVVP LLP valsegment Type@AV: 55.6 -> 63.4Improved
use CLIP and CLAP features instead of ResNet-152 and VGGish (ablation)Valor · AVVP LLP valsegment Type@AV: 64.9 -> 68.6Improved
thinner yet deeper HAN (4 layers, 256-dim) (ablation)Valor · AVVP LLP valsegment Type@AV: 63.4 -> 64.9Improved
distill dense labels with KD loss instead of Valor labels (ablation)HAN baseline · AVVP LLP valsegment Type@AV: 55.6 -> 54.3Hurt
remove video-level labels as filters (audio) (ablation)Valor · AVVP LLP valaudio F-score: 63.4 -> 47.9Hurt
remove video-level labels as filters (visual) (ablation)Valor · AVVP LLP valvisual F-score: 65.9 -> 53.8Hurt
class-dependent instead of unified thresholds (ablation)Valor · AVVP LLP valsegment Type@AV: 63.1 -> 63.4No clear effect
apply pseudo label denoising (PLD) to Valor labels (ablation)Valor · LLP val visual segment fidelityF-score: 72.34 -> 73.84Improved
apply PLD before training (ablation)Valor · AVVP LLP testsegment Type@AV: 62.0 -> 62.2No clear effect

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