{"total":18,"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":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"area":null},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33,"area":null},{"id":"2104.11984","title":"MusCaps: Generating Captions for Music Audio","created":"2021-04-24","cited_by_count":23,"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":"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":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"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":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2110.07410","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2204.08409","title":"Caption Feature Space Regularization for Audio Captioning","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2105.06355","title":"Audio Captioning with Composition of Acoustic and Semantic Information","created":"2021-05-13","cited_by_count":1,"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":"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":"2501.03183","title":"Classifier-Guided Captioning Across Modalities","created":"2025-01-03","cited_by_count":0,"area":null}],"next_cursor":null}