{"list":"other","total":61,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"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":"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":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","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":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"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":"2404.10301","title":"Long-form music generation with latent diffusion","created":"2024-04-16","cited_by_count":89},{"id":"2311.07069","title":"Music ControlNet: Multiple Time-varying Controls for Music Generation","created":"2023-11-13","cited_by_count":83},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"2302.02257","title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","created":"2023-02-04","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":"2207.02127","title":"A survey of multimodal deep generative models","created":"2022-07-05","cited_by_count":47},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29},{"id":"2107.09998","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","created":"2021-07-21","cited_by_count":24},{"id":"2310.15247","title":"SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis","created":"2023-10-23","cited_by_count":24},{"id":"2409.08601","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","created":"2024-09-13","cited_by_count":21},{"id":"2107.09262","title":"FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos","created":"2021-07-20","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":"2401.09294","title":"T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis","created":"2024-01-17","cited_by_count":19},{"id":"2409.17550","title":"A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation","created":"2024-09-26","cited_by_count":19},{"id":"2302.07702","title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision","created":"2023-02-15","cited_by_count":18},{"id":"2403.16276","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","created":"2024-03-24","cited_by_count":18},{"id":"2408.11915","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","created":"2024-08-21","cited_by_count":16},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13},{"id":"2211.10666","title":"VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement","created":"2022-11-19","cited_by_count":11},{"id":"2404.16305","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","created":"2024-04-25","cited_by_count":11},{"id":"2202.10372","title":"L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment","created":"2022-02-21","cited_by_count":10},{"id":"2406.08802","title":"DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing","created":"2024-06-13","cited_by_count":10},{"id":"2104.05499","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","created":"2021-04-12","cited_by_count":9},{"id":"2110.09605","title":"Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks","created":"2021-10-18","cited_by_count":4},{"id":"2305.15905","title":"Latent Diffusion Model Based Foley Sound Generation System For DCASE Challenge 2023 Task 7","created":"2023-05-25","cited_by_count":4},{"id":"2408.10998","title":"Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos","created":"2024-08-20","cited_by_count":4},{"id":"2409.09823","title":"Efficient Video to Audio Mapper with Visual Scene Detection","created":"2024-09-15","cited_by_count":4},{"id":"2409.09162","title":"MambaFoley: Foley Sound Generation using Selective State-Space Models","created":"2024-09-13","cited_by_count":3}],"next_cursor":null}