{"total":46,"rows":[{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2404.10989","title":"FairSSD: Understanding Bias in Synthetic Speech Detectors","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2312.15190","title":"SAIC: Integration of Speech Anonymization and Identity Classification","created":"2023-12-23","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2304.03323","title":"DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection","created":"2023-04-06","cited_by_count":6,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2307.09286","title":"FlexiAST: Flexibility is What AST Needs","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2309.10930","title":"Test-Time Training for Speech","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2405.08679","title":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2301.12058","title":"Aerial Image Object Detection With Vision Transformer Detector (ViTDet)","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2412.15622","title":"TouchASP: Elastic Automatic Speech Perception that Everyone Can Touch","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2502.12511","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2308.07221","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2308.11859","title":"Example-Based Framework for Perceptually Guided Audio Texture Generation","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2401.08415","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2402.14205","title":"Compression Robust Synthetic Speech Detection Using Patched Spectrogram Transformer","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2407.20989","title":"Contrasting Deep Learning Models for Direct Respiratory Insufficiency Detection Versus Blood Oxygen Saturation Estimation","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2502.00859","title":"FedRIR: Rethinking Information Representation in Federated Learning","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2306.05915","title":"Speaker Embeddings as Individuality Proxy for Voice Stress Detection","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2306.11764","title":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2403.09579","title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2507.10464","title":"AudioMAE++: learning better masked audio representations with SwiGLU FFNs","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.20622","title":"Masked Autoencoders for Ultrasound Signals: Robust Representation Learning for Downstream Applications","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2601.21612","title":"Representation-Regularized Convolutional Audio Transformer for Audio Understanding","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02413","title":"Masked Autoencoders as Universal Speech Enhancer","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.13749","title":"Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.15221","title":"MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}