{"total":42,"rows":[{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"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":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2206.12513","title":"Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2110.07607","title":"HumBugDB: A Large-scale Acoustic Mosquito Dataset","created":"2021-10-14","cited_by_count":15,"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":"2206.07511","title":"Investigating Multi-Feature Selection and Ensembling for Audio Classification","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2302.05940","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2104.10116","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2305.16691","title":"Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2103.01929","title":"SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification","created":"2021-03-02","cited_by_count":4,"area":null},{"id":"2206.13231","title":"QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2304.11648","title":"Towards Controllable Audio Texture Morphing","created":"2023-04-23","cited_by_count":4,"area":null},{"id":"2309.04762","title":"AudRandAug: Random Image Augmentations for Audio Classification","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2305.13033","title":"Towards generalizing deep-audio fake detection networks","created":"2023-05-22","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":"2106.11335","title":"Do sound event representations generalize to other audio tasks? A case study in audio transfer learning","created":"2021-06-21","cited_by_count":1,"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":"2110.07778","title":"NeuroView: Explainable Deep Network Decision Making","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2204.07763","title":"UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio","created":"2022-04-16","cited_by_count":1,"area":null},{"id":"2308.11859","title":"Example-Based Framework for Perceptually Guided Audio Texture Generation","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2310.04722","title":"A Holistic Evaluation of Piano Sound Quality","created":"2023-10-07","cited_by_count":1,"area":null},{"id":"2408.15667","title":"Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2501.03464","title":"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2202.03514","title":"Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study","created":"2022-02-07","cited_by_count":0,"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":"2205.11748","title":"Deep Learning-based automated classification of Chinese Speech Sound Disorders","created":"2022-05-24","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":"2302.03533","title":"Revisiting Pre-training in Audio-Visual Learning","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2302.07640","title":"Detection and classification of vocal productions in large scale audio recordings","created":"2023-02-14","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":"2402.10100","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2410.23325","title":"Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-soprano","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2412.05951","title":"When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2506.11049","title":"15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2508.10828","title":"A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.05307","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2609.17884","title":"The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.27762","title":"\"What's That Sound?\": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}