{"total":50,"rows":[{"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":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"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":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2203.15526","title":"Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning","created":"2022-03-29","cited_by_count":15,"area":null},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2108.04692","title":"Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2210.17143","title":"Exploring Train and Test-Time Augmentations for Audio-Language Learning","created":"2022-10-31","cited_by_count":11,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2407.07801","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2201.03217","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2202.01405","title":"Joint Speech Recognition and Audio Captioning","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2309.02405","title":"Generating Realistic Images from In-the-wild Sounds","created":"2023-09-05","cited_by_count":4,"area":null},{"id":"2210.05037","title":"Automated Audio Captioning via Fusion of Low- and High- Dimensional Features","created":"2022-10-10","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":"2309.03884","title":"Zero-Shot Audio Captioning via Audibility Guidance","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2409.01201","title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2505.22045","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2207.04156","title":"Automated Audio Captioning and Language-Based Audio Retrieval","created":"2022-07-08","cited_by_count":2,"area":null},{"id":"2308.11923","title":"Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2210.06354","title":"Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2409.01160","title":"Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2501.03038","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2206.01918","title":"Automated Audio Captioning with Epochal Difficult Captions for Curriculum Learning","created":"2022-06-04","cited_by_count":0,"area":null},{"id":"2304.02916","title":"Efficient Audio Captioning Transformer with Patchout and Text Guidance","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2306.10090","title":"Improving Audio Caption Fluency with Automatic Error Correction","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2309.08141","title":"Audio Difference Learning for Audio Captioning","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2405.00367","title":"Distance Sampling-based Paraphraser Leveraging ChatGPT for Text Data Manipulation","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2602.17599","title":"Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.26804","title":"The Language of Touch: Translating Vibrations into Text with Dual-Branch Learning","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.25197","title":"LGFNet: A CTC-Guided Local-Global Fusion Framework for Single-Channel Sleep Staging","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}