AI Paper Atlas

Research map / Video / Video segmentation and tracking

MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing

Langyu Wang, Bingke Zhu, Yingying Chen, Yiyuan Zhang, Ming Tang, Jinqiao Wang

ICCV 2025 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 4 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
add cross modality random combination (CMRC) augmentation (ablation)MUG · LLP segment-levelType@AV: 62.2 -> 63.9Improved
add CMRC augmentation (ablation)MUG · LLP event-levelType@AV: 57.4 -> 59.6Improved
add Mamba-based attention (MBA) (ablation)MUG · LLP segment-levelType@AV: 63.3 -> 63.9Improved
add adaptive mamba fusion (AMF) (ablation)MUG · LLP segment-levelType@AV: 63.4 -> 63.9Improved
add Mamba feature enhancement (MFE) (ablation)MUG · LLP segment-levelType@AV: 62.4 -> 63.9Improved
add pseudo-label semantic interaction module (PLSIM) (ablation)MUG · LLP segment-levelType@AV: 63.7 -> 63.9Improved
add CMRC to HANHAN · LLP segment-levelType@AV: 54.0 -> 54.9Improved
add CMRC to MGNMGN · LLP segment-levelType@AV: 55.5 -> 57.3Improved
add CMRC to JoMoLDJoMoLD · LLP segment-levelType@AV: 60.8 -> 61.7Improved
increase CMRC data from 1585 (Batch1) to 6080 (Batch4) samples (ablation)MUG · LLP segment-levelType@AV: 62.7 -> 63.9Improved
double generated data again (Batch4 to Batch5) (ablation)MUG · LLP segment-levelEvent@AV: 64.7 -> 64.9Mixed
replace Mamba with Transformer attention (ablation)MUG · LLP segment-levelType@AV: 63.9 -> 62.7Hurt

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