{"total":20,"rows":[{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"area":null},{"id":"2305.14330","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","created":"2023-05-23","cited_by_count":49,"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":"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":"2502.19781","title":"RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings","created":"2025-02-27","cited_by_count":19,"area":null},{"id":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18,"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":"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":"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":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2308.11923","title":"Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2402.15746","title":"Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2509.12591","title":"MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2201.12352","title":"Automatic Audio Captioning using Attention weighted Event based Embeddings","created":"2022-01-28","cited_by_count":0,"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}],"next_cursor":null}