{"total":19,"rows":[{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"area":null},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2311.10986","title":"EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge","created":"2023-11-18","cited_by_count":21,"area":null},{"id":"2304.07382","title":"Zero-Shot Multi-Label Topic Inference with Sentence Encoders","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2309.08398","title":"Exploring Meta Information for Audio-based Zero-shot Bird Classification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2407.19893","title":"Leveraging Foundation Models for Zero-Shot IoT Sensing","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2206.04984","title":"Zero-Shot Audio Classification using Image Embeddings","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2208.11402","title":"Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers","created":"2022-08-24","cited_by_count":2,"area":null},{"id":"2409.00408","title":"Multi-label Zero-Shot Audio Classification with Temporal Attention","created":"2024-08-31","cited_by_count":2,"area":null},{"id":"2503.02993","title":"Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2505.19938","title":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2106.10277","title":"GPLA-12: An Acoustic Signal Dataset of Gas Pipeline Leakage","created":"2021-06-19","cited_by_count":1,"area":null},{"id":"2311.02482","title":"Generalized zero-shot audio-to-intent classification","created":"2023-11-04","cited_by_count":1,"area":null},{"id":"2408.13068","title":"On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2203.06064","title":"Climate Change & Computer Audition: A Call to Action and Overview on Audio Intelligence to Help Save the Planet","created":"2022-03-10","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":"2609.31168","title":"Audio emotion recognition for atypical hearing","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}