{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"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":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"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":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2301.07733","title":"Learning-Rate-Free Learning by D-Adaptation","created":"2023-01-18","cited_by_count":113},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","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":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37},{"id":"2311.00968","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","created":"2023-11-02","cited_by_count":37},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29},{"id":"2111.13457","title":"Semi-Supervised Music Tagging Transformer","created":"2021-11-26","cited_by_count":25},{"id":"2303.16897","title":"Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos","created":"2023-03-29","cited_by_count":22},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17},{"id":"2405.12221","title":"Images that Sound: Composing Images and Sounds on a Single Canvas","created":"2024-05-20","cited_by_count":17},{"id":"2306.13512","title":"DISCO-10M: A Large-Scale Music Dataset","created":"2023-06-23","cited_by_count":13}],"next_cursor":null}