{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2109.00537","title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection","created":"2021-09-01","cited_by_count":161},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2009.12981","title":"Parametric UMAP embeddings for representation and semi-supervised learning","created":"2020-09-27","cited_by_count":104},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"1704.08292","title":"Deep Cross-Modal Audio-Visual Generation","created":"2017-04-26","cited_by_count":63},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37},{"id":"1711.08102","title":"CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation","created":"2017-11-22","cited_by_count":31},{"id":"2306.09635","title":"CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models","created":"2023-06-16","cited_by_count":20},{"id":"2002.10981","title":"AutoFoley: Artificial Synthesis of Synchronized Sound Tracks for Silent Videos with Deep Learning","created":"2020-02-21","cited_by_count":19},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13},{"id":"2303.03857","title":"Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study","created":"2023-03-07","cited_by_count":10},{"id":"2302.08575","title":"Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media","created":"2023-02-16","cited_by_count":8}],"next_cursor":null}