{"total":24,"rows":[{"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":"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":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"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":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"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":"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":"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":"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":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"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":"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":"2204.08409","title":"Caption Feature Space Regularization for Audio Captioning","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2407.20989","title":"Contrasting Deep Learning Models for Direct Respiratory Insufficiency Detection Versus Blood Oxygen Saturation Estimation","created":"2024-07-30","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":"2203.17012","title":"A Temporal-oriented Broadcast ResNet for COVID-19 Detection","created":"2022-03-31","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":"2208.06127","title":"An investigation on selecting audio pre-trained models for audio captioning","created":"2022-08-12","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}