{"total":22,"rows":[{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56,"area":null},{"id":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","cited_by_count":18,"area":null},{"id":"2105.12395","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2103.13620","title":"SubSpectral Normalization for Neural Audio Data Processing","created":"2021-03-25","cited_by_count":11,"area":null},{"id":"2305.07499","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2206.13909","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2204.04250","title":"Understanding the Influence of Receptive Field and Network Complexity in Neural-Network-Guided TEM Image Analysis","created":"2022-04-08","cited_by_count":9,"area":null},{"id":"2104.13620","title":"IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2111.06531","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2211.13956","title":"Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2303.11508","title":"AI-in-the-Loop -- The impact of HMI in AI-based Application","created":"2023-03-21","cited_by_count":4,"area":null},{"id":"2102.08833","title":"DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2101.11704","title":"A Case Study of Deep Learning Based Multi-Modal Methods for Predicting the Age-Suitability Rating of Movie Trailers","created":"2021-01-26","cited_by_count":2,"area":null},{"id":"2102.13479","title":"Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features via Acoustic Domain Adaptation","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2207.08001","title":"SVGraph: Learning Semantic Graphs from Instructional Videos","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2312.01662","title":"Universal Deoxidation of Semiconductor Substrates Assisted by Machine-Learning and Real-Time-Feedback-Control","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2107.08933","title":"Over-Parameterization and Generalization in Audio Classification","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2111.07979","title":"Metric-based multimodal meta-learning for human movement identification via footstep recognition","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2401.09823","title":"Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layer","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2503.16862","title":"Improving Acoustic Scene Classification with City Features","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2508.16970","title":"Local Information Matters: A Rethink of Crowd Counting","created":"2025-08-23","cited_by_count":0,"area":null}],"next_cursor":null}