Structured-Noise Masked Modeling for Video, Audio and Beyond
cs.LG, cs.AI, cs.SD
Submitted: 2025-03-20
Updated: 2026-09-30
Terminology
Sources
- MAE-AST: Masked Autoencoding Audio Spectrogram Transformer
- BEiT: BERT Pre-Training of Image Transformers
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- AST: Audio Spectrogram Transformer
- Contrastive Audio-Visual Masked Autoencoder
- The Kinetics Human Action Video Dataset
- CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- The 2017 DAVIS Challenge on Video Object Segmentation
- wav2vec: Unsupervised Pre-training for Speech Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Rethinking the Inception Architecture for Computer Vision
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- Masked Frequency Modeling for Self-Supervised Visual Pre-Training
- YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
- mixup: Beyond Empirical Risk Minimization
- iBOT: Image BERT Pre-Training with Online Tokenizer
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks