{"total":39,"rows":[{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"area":null},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2104.11984","title":"MusCaps: Generating Captions for Music Audio","created":"2021-04-24","cited_by_count":23,"area":null},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2211.01317","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2110.09127","title":"SpecTNT: a Time-Frequency Transformer for Music Audio","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2112.04214","title":"Learning music audio representations via weak language supervision","created":"2021-12-08","cited_by_count":13,"area":null},{"id":"2102.04680","title":"Tr\\\"aumerAI: Dreaming Music with StyleGAN","created":"2021-02-09","cited_by_count":11,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"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":"2211.07131","title":"YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2312.11234","title":"Perceptual Musical Features for Interpretable Audio Tagging","created":"2023-12-18","cited_by_count":7,"area":null},{"id":"2409.11264","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2206.10805","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2107.00623","title":"Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2307.09795","title":"From West to East: Who can understand the music of the others better?","created":"2023-07-19","cited_by_count":5,"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":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2110.08862","title":"Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2210.00434","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2302.00286","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","created":"2023-02-01","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":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2103.01893","title":"Listen, Read, and Identify: Multimodal Singing Language Identification of Music","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2110.13071","title":"Unsupervised Source Separation By Steering Pretrained Music Models","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2309.00347","title":"Towards Contrastive Learning in Music Video Domain","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2309.01340","title":"MDSC: Towards Evaluating the Style Consistency Between Music and Dance","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2407.02156","title":"Towards Training Music Taggers on Synthetic Data","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2409.07730","title":"Music auto-tagging in the long tail: A few-shot approach","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2104.02309","title":"MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2105.11836","title":"A Modulation Front-End for Music Audio Tagging","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2304.07449","title":"Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging","created":"2023-04-15","cited_by_count":0,"area":null},{"id":"2504.09289","title":"Sparse Hybrid Linear-Morphological Networks","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2505.06042","title":"Learning Music Audio Representations With Limited Data","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2610.06920","title":"Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}