{"total":26,"rows":[{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2110.08858","title":"Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks","created":"2021-10-17","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":"2110.09127","title":"SpecTNT: a Time-Frequency Transformer for Music Audio","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2105.13854","title":"Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2203.09129","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2206.07511","title":"Investigating Multi-Feature Selection and Ensembling for Audio Classification","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2109.10038","title":"VPN: Video Provenance Network for Robust Content Attribution","created":"2021-09-21","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":"2103.01904","title":"A Spectral Enabled GAN for Time Series Data Generation","created":"2021-03-02","cited_by_count":6,"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":"2209.03759","title":"Representation Learning for Appliance Recognition: A Comparison to Classical Machine Learning","created":"2022-08-26","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":"2309.04762","title":"AudRandAug: Random Image Augmentations for Audio Classification","created":"2023-09-09","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":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2401.15323","title":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","created":"2024-01-27","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":"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":"2306.16054","title":"Improving Primate Sounds Classification using Binary Presorting for Deep Learning","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2410.20352","title":"An approach to hummed-tune and song sequences matching","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2505.17233","title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2608.30974","title":"CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}