{"total":17,"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":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"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":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2302.04061","title":"Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2103.04344","title":"Graph Force Learning","created":"2021-03-07","cited_by_count":3,"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":"2212.02033","title":"Towards Generating Diverse Audio Captions via Adversarial Training","created":"2022-12-05","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":"2103.00833","title":"Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning","created":"2021-03-01","cited_by_count":2,"area":null},{"id":"2205.14428","title":"Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregation","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2504.15214","title":"Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2602.20461","title":"Nonparametric Teaching of Attention Learners","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.17025","title":"Shared Representation Learning for Reference-Guided Targeted Sound Detection","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.22218","title":"An Analysis of Untrained Deep Reservoir Networks for Audio Surveillance","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.20326","title":"$TCP_\\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval","created":"2026-08-20","cited_by_count":0,"area":null}],"next_cursor":null}