AI Paper Atlas

Research map / Video / Video segmentation and tracking

MAViL: Masked Audio-Video Learners

Po-Yao Huang, Vasu Sharma, Hu Xu, Chaitanya Ryali, Haoqi Fan, Yanghao Li, Shang-Wen Li, Gargi Ghosh, Jitendra Malik, Christoph Feichtenhofer

NeurIPS 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 17 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 masked contrastive learning (inter+intra) to joint AV-MAE (ablation)MAViL stage-1 · AS-20K audiomAP: 36.8 -> 39.0Improved
add masked contrastive learning (inter+intra) (ablation)MAViL stage-1 · AS-20K videomAP: 17.7 -> 22.2Improved
add intra-modal contrast on top of inter-modal only (ablation)MAViL stage-1 · AS-20K audiomAP: 38.4 -> 39.0Improved
add audio-video fusion encoder (ablation)uni-modal MAE · AS-20K audiomAP: 36.4 -> 36.8Improved
MBT instead of vanilla Transformer fusion encoder (ablation)fusion encoder · AS-20KmAP: 36.8 -> 36.8 (audio)No clear effect
stage-2 self-training to predict teacher contextualized representations instead of raw targets (ablation)MAViL · AS-20K audiomAP: 39.0 -> 41.8Improved
use multimodal fusion output of teacher as target vs uni-modal output (ablation)MAViL stage-2 · AS-20K audiomAP: 40.2 -> 40.7Improved
increase self-training iterations from 1 to 3 (ablation)MAViL stage-2 · AS-20K audiomAP: 40.7 -> 41.8Improved
raise masking ratio from 40% to 80% (ablation)MAViL stage-1 · AS-20K audiomAP: 35.6 -> 36.8Improved
raise masking ratio from 80% to 90% (ablation)MAViL stage-1 · AS-20K videomAP: 17.7 -> 17.5Hurt
initialize visual backbone with ImageNet SSL MAE (ablation)MAViL · AS-20K videomAP: 23.7 -> 24.8Improved
increase encoder size ViT-B to ViT-L (ablation)MAViL · AS-20K audiomAP: 41.8 -> 42.2Improved

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