{"total":28,"rows":[{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"area":null},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2112.08995","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2203.15526","title":"Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning","created":"2022-03-29","cited_by_count":15,"area":null},{"id":"2103.02420","title":"Multi-view Audio and Music Classification","created":"2021-03-03","cited_by_count":8,"area":null},{"id":"2208.01141","title":"SampleMatch: Drum Sample Retrieval by Musical Context","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2104.10116","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2103.03483","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2103.01929","title":"SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification","created":"2021-03-02","cited_by_count":4,"area":null},{"id":"2211.02940","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2309.04762","title":"AudRandAug: Random Image Augmentations for Audio Classification","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2102.08183","title":"Comparison of semi-supervised deep learning algorithms for audio classification","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2308.09089","title":"Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2409.11059","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2110.07778","title":"NeuroView: Explainable Deep Network Decision Making","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2406.17190","title":"Sound Tagging in Infant-centric Home Soundscapes","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2105.09279","title":"Unsupervised Discriminative Learning of Sounds for Audio Event Classification","created":"2021-05-19","cited_by_count":0,"area":null},{"id":"2202.03514","title":"Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2311.12130","title":"Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2311.15386","title":"Spectro-ViT: A Vision Transformer Model for GABA-edited MRS Reconstruction Using Spectrograms","created":"2023-11-26","cited_by_count":0,"area":null},{"id":"2410.23325","title":"Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-soprano","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2603.25476","title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2606.00081","title":"DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.22220","title":"MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning","created":"2026-06-20","cited_by_count":0,"area":null}],"next_cursor":null}