{"total":36,"rows":[{"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":"2102.03229","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","created":"2021-02-05","cited_by_count":18,"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":"2201.06268","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","created":"2022-01-17","cited_by_count":12,"area":null},{"id":"2207.11229","title":"Flow Moods: Recommending Music by Moods on Deezer","created":"2022-07-15","cited_by_count":11,"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":"2305.19602","title":"Learning Music Sequence Representation from Text Supervision","created":"2023-05-31","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":"2210.14716","title":"Pretrained audio neural networks for Speech emotion recognition in Portuguese","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2305.12712","title":"LEAN: Light and Efficient Audio Classification Network","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2407.06060","title":"MERGE -- A Bimodal Audio-Lyrics Dataset for Static Music Emotion Recognition","created":"2024-07-08","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":"2306.07310","title":"Employing Crowdsourcing for Enriching a Music Knowledge Base in Higher Education","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2410.19760","title":"Movie Trailer Genre Classification Using Multimodal Pretrained Features","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2412.03214","title":"Continual Low-Rank Scaled Dot-product Attention","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2107.13237","title":"A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification","created":"2021-07-28","cited_by_count":1,"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":"2406.13579","title":"Automated Bioacoustic Monitoring for South African Bird Species on Unlabeled Data","created":"2024-06-19","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":"2107.06231","title":"Timbre Classification of Musical Instruments with a Deep Learning Multi-Head Attention-Based Model","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2110.04765","title":"Multi-task Learning with Metadata for Music Mood Classification","created":"2021-10-10","cited_by_count":0,"area":null},{"id":"2305.15084","title":"Audio-Visual Dataset and Method for Anomaly Detection in Traffic Videos","created":"2023-05-24","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":"2401.00209","title":"AI and Tempo Estimation: A Review","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2407.01499","title":"Pictures Of MIDI: Controlled Music Generation via Graphical Prompts for Image-Based Diffusion Inpainting","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2407.05368","title":"Music Era Recognition Using Supervised Contrastive Learning and Artist Information","created":"2024-07-07","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":"2501.01094","title":"MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2505.23784","title":"Learning Normal Patterns in Musical Loops","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.25114","title":"Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}