{"list":"other","total":85,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"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":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"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":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"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":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"1802.04034","title":"Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks","created":"2018-02-12","cited_by_count":195},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"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":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"1804.01452","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","created":"2018-04-04","cited_by_count":81},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"1903.01014","title":"Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators","created":"2019-03-03","cited_by_count":55},{"id":"2401.01044","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","created":"2024-01-02","cited_by_count":54},{"id":"1701.00495","title":"Vid2speech: Speech Reconstruction from Silent Video","created":"2017-01-02","cited_by_count":53},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"1904.09013","title":"Self-Supervised Audio-Visual Co-Segmentation","created":"2019-04-18","cited_by_count":44},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29},{"id":"2303.10667","title":"Audio-Text Models Do Not Yet Leverage Natural Language","created":"2023-03-19","cited_by_count":26},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18},{"id":"2406.05629","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","created":"2024-06-09","cited_by_count":17},{"id":"2304.06818","title":"Soundini: Sound-Guided Diffusion for Natural Video Editing","created":"2023-04-13","cited_by_count":14},{"id":"2405.18503","title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","created":"2024-05-28","cited_by_count":9},{"id":"2005.09200","title":"Atss-Net: Target Speaker Separation via Attention-based Neural Network","created":"2020-05-19","cited_by_count":8},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8}],"next_cursor":null}