{"total":26,"rows":[{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131,"area":null},{"id":"2107.09998","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","created":"2021-07-21","cited_by_count":24,"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":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2203.09581","title":"SepTr: Separable Transformer for Audio Spectrogram Processing","created":"2022-03-17","cited_by_count":15,"area":null},{"id":"2410.17785","title":"TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2109.00962","title":"You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2403.08525","title":"From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning","created":"2024-03-13","cited_by_count":4,"area":null},{"id":"2210.11328","title":"Play It Back: Iterative Attention for Audio Recognition","created":"2022-10-20","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":"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":"2105.13392","title":"Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2303.05678","title":"Improving Weakly Supervised Sound Event Detection with Causal Intervention","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2307.01663","title":"Exploring Transformers for On-Line Handwritten Signature Verification","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2207.03927","title":"BAST: Binaural Audio Spectrogram Transformer for Binaural Sound Localization","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2306.14191","title":"PrimaDNN': A Characteristics-aware DNN Customization for Singing Technique Detection","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2111.07382","title":"Adaptive Cost-Sensitive Learning in Neural Networks for Misclassification Cost Problems","created":"2021-11-14","cited_by_count":0,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","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":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2312.16228","title":"Deformable Audio Transformer for Audio Event Detection","created":"2023-12-24","cited_by_count":0,"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":"2608.14287","title":"Acoustic UAV Detection in Battlefield Scenarios: Handling Noise, Domain Shift, and Weak Labels","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.15221","title":"MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}