{"total":76,"rows":[{"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":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"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":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","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":"2403.01255","title":"Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey","created":"2024-03-02","cited_by_count":50,"area":null},{"id":"2310.14753","title":"Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules","created":"2023-10-23","cited_by_count":49,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2404.06393","title":"MuPT: A Generative Symbolic Music Pretrained Transformer","created":"2024-04-09","cited_by_count":33,"area":null},{"id":"2502.08869","title":"Harnessing Vision Models for Time Series Analysis: A Survey","created":"2025-02-13","cited_by_count":26,"area":null},{"id":"2305.14032","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","created":"2023-05-23","cited_by_count":24,"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":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16,"area":null},{"id":"2411.10830","title":"One-Layer Transformer Provably Learns One-Nearest Neighbor In Context","created":"2024-11-16","cited_by_count":16,"area":null},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"area":null},{"id":"2211.13189","title":"ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"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":"2304.11117","title":"A vector quantized masked autoencoder for speech emotion recognition","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2505.20027","title":"Multi-modal brain encoding models for multi-modal stimuli","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2210.01632","title":"Backdoor Attacks in the Supply Chain of Masked Image Modeling","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"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":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"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":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2210.11328","title":"Play It Back: Iterative Attention for Audio Recognition","created":"2022-10-20","cited_by_count":3,"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":"2304.04385","title":"On Robustness in Multimodal Learning","created":"2023-04-10","cited_by_count":3,"area":null},{"id":"2409.17656","title":"Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2502.10718","title":"Hyperdimensional Intelligent Sensing for Efficient Real-Time Audio Processing on Extreme Edge","created":"2025-02-15","cited_by_count":3,"area":null},{"id":"2311.03314","title":"FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2405.07202","title":"Unified Video-Language Pre-training with Synchronized Audio","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2407.08691","title":"ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions","created":"2024-07-11","cited_by_count":2,"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":"2401.08415","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2401.10544","title":"AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks","created":"2024-01-19","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":"2503.16311","title":"Structured-Noise Masked Modeling for Video, Audio and Beyond","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2605.14031","title":"Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study","created":"2026-05-13","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":"2606.14791","title":"From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2305.00417","title":"Transformer-based Sequence Labeling for Audio Classification based on MFCCs","created":"2023-04-30","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":"2412.05951","title":"When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2502.02118","title":"BRIDLE: Generalized Self-supervised Learning with Quantization","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2505.21025","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","created":"2025-05-27","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":"2508.20983","title":"Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.10719","title":"SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2511.02938","title":"From Narrow to Wide: Autoencoding Transformers for Ultrasound Bandwidth Recovery","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.00496","title":"CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2512.03637","title":"AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers","created":"2025-12-03","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":"2603.01482","title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.26098","title":"A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.30700","title":"BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations","created":"2026-06-29","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":"2608.25794","title":"Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27578","title":"Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.15067","title":"Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.34030","title":"Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}