{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"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":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"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":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"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":"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":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"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":"1710.04196","title":"Pyroomacoustics: A Python package for audio room simulations and array processing algorithms","created":"2017-10-11","cited_by_count":132},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","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":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"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":"1608.07017","title":"Ambient Sound Provides Supervision for Visual Learning","created":"2016-08-25","cited_by_count":78},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","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":"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":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","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":"2001.01656","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","created":"2020-01-06","cited_by_count":38},{"id":"1706.00932","title":"See, Hear, and Read: Deep Aligned Representations","created":"2017-06-03","cited_by_count":32},{"id":"1805.04792","title":"Scene-Aware Audio for 360\\textdegree{} Videos","created":"2018-05-12","cited_by_count":25},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"2312.00834","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","created":"2023-11-30","cited_by_count":20},{"id":"2111.08046","title":"Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention","created":"2021-11-15","cited_by_count":17},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15},{"id":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14},{"id":"2310.20446","title":"LAVSS: Location-Guided Audio-Visual Spatial Audio Separation","created":"2023-10-31","cited_by_count":8}],"next_cursor":null}