{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"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":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"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":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"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":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70},{"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":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68},{"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":"2410.05677","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","created":"2024-10-08","cited_by_count":54},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2409.13689","title":"Temporally Aligned Audio for Video with Autoregression","created":"2024-09-20","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":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35},{"id":"2304.02970","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","created":"2023-04-06","cited_by_count":34},{"id":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32},{"id":"2403.00522","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","created":"2024-03-01","cited_by_count":28},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21},{"id":"2409.08601","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","created":"2024-09-13","cited_by_count":21},{"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":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15},{"id":"2410.12957","title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","created":"2024-10-16","cited_by_count":14},{"id":"2404.16305","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","created":"2024-04-25","cited_by_count":11},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7},{"id":"2407.20592","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","created":"2024-07-30","cited_by_count":6},{"id":"2409.08628","title":"Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis","created":"2024-09-13","cited_by_count":5},{"id":"2411.01805","title":"MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence","created":"2024-11-04","cited_by_count":5},{"id":"2407.05782","title":"Sequential Contrastive Audio-Visual Learning","created":"2024-07-08","cited_by_count":2}],"next_cursor":null}