AI Paper Atlas

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

Multimodal Variational Auto-encoder based Audio-Visual Segmentation

Yuxin Mao, Jing Zhang, Mochu Xiang, Yiran Zhong, Yuchao Dai

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 62 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 audio in a multimodal VAE rather than video-only CVAE (ablation)ECMVAE · AVSBench MS3mIoU: 49.26 -> 54.99Improved
add latent space factorization into shared and specific codes (ablation)ECMVAE · AVSBench MS3mIoU: 54.99 -> 56.38Improved
double the latent dimension without factorization (ablation)ECMVAE · AVSBench MS3mIoU: 54.99 -> 55.09No clear effect
factorize in VAE latent space rather than AE feature space (ablation)ECMVAE · AVSBench MS3mIoU: 54.82 -> 56.38Improved
use JS divergence instead of KL, PoE or MoE (ablation)ECMVAE · AVSBench MS3mIoU: 57.53 -> 57.84Improved
add orthogonality constraint L_diff (ablation)ECMVAE · AVSBench MS3mIoU: 57.51 -> 58.15Improved
add mutual information maximization L_sic (ablation)ECMVAE · AVSBench MS3mIoU: 57.51 -> 57.84Improved
pre-train on S4 subsetECMVAE (PVT) · AVSBench MS3mIoU: 57.84 -> 60.81Improved
pre-train on S4 subsetECMVAE (R50) · AVSBench MS3mIoU: 48.69 -> 57.56Improved

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