{"total":14,"rows":[{"id":"2302.06232","title":"Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data","created":"2023-02-13","cited_by_count":43,"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":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"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":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"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":"2202.09750","title":"Enhancing Affective Representations of Music-Induced EEG through Multimodal Supervision and latent Domain Adaptation","created":"2022-02-20","cited_by_count":3,"area":null},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2312.09207","title":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2502.12623","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2212.01033","title":"Sonus Texere! Automated Dense Soundtrack Construction for Books using Movie Adaptations","created":"2022-12-02","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":"2504.21772","title":"Solving Copyright Infringement on Short Video Platforms: Novel Datasets and an Audio Restoration Deep Learning Pipeline","created":"2025-04-30","cited_by_count":0,"area":null}],"next_cursor":null}