{"total":117,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985,"area":null},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484,"area":null},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301,"area":null},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205,"area":null},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182,"area":null},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"area":null},{"id":"2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","created":"2022-07-12","cited_by_count":152,"area":null},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"area":null},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"area":null},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2102.04432","title":"Colorization Transformer","created":"2021-02-08","cited_by_count":89,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48,"area":null},{"id":"2107.07224","title":"StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN","created":"2021-07-15","cited_by_count":47,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2102.09532","title":"Clockwork Variational Autoencoders","created":"2021-02-18","cited_by_count":42,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38,"area":null},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37,"area":null},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37,"area":null},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2303.09998","title":"TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving","created":"2023-03-17","cited_by_count":30,"area":null},{"id":"2404.12388","title":"VideoGigaGAN: Towards Detail-rich Video Super-Resolution","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30,"area":null},{"id":"2204.07172","title":"Diagnosing and Fixing Manifold Overfitting in Deep Generative Models","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2207.09840","title":"EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer","created":"2022-07-20","cited_by_count":28,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2209.07143","title":"HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator","created":"2022-09-15","cited_by_count":22,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21,"area":null},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2303.10126","title":"IRGen: Generative Modeling for Image Retrieval","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2206.14797","title":"3D-Aware Video Generation","created":"2022-06-29","cited_by_count":17,"area":null},{"id":"2212.04655","title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","created":"2022-12-09","cited_by_count":17,"area":null},{"id":"2312.08403","title":"Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model","created":"2023-12-13","cited_by_count":17,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2312.12917","title":"Sign Language Production with Latent Motion Transformer","created":"2023-12-20","cited_by_count":13,"area":null},{"id":"2404.13573","title":"Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap","created":"2024-04-21","cited_by_count":13,"area":null},{"id":"2212.07413","title":"Towards Smooth Video Composition","created":"2022-12-14","cited_by_count":12,"area":null},{"id":"2303.03684","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","created":"2023-03-07","cited_by_count":12,"area":null},{"id":"2410.17751","title":"VISAGE: Video Synthesis using Action Graphs for Surgery","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2206.03697","title":"Blind Face Restoration: Benchmark Datasets and a Baseline Model","created":"2022-06-08","cited_by_count":10,"area":null},{"id":"2106.14014","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","created":"2021-06-26","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2402.05970","title":"Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2510.05613","title":"PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction","created":"2025-10-07","cited_by_count":9,"area":null},{"id":"2104.01122","title":"M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers","created":"2021-04-02","cited_by_count":8,"area":null},{"id":"2109.04683","title":"PIP: Physical Interaction Prediction via Mental Simulation with Span Selection","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2201.02715","title":"Low-Rank Constraints for Fast Inference in Structured Models","created":"2022-01-08","cited_by_count":8,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2501.08303","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2111.12747","title":"Layered Controllable Video Generation","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2209.11223","title":"UniColor: A Unified Framework for Multi-Modal Colorization with Transformer","created":"2022-09-22","cited_by_count":7,"area":null},{"id":"2306.03988","title":"Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2412.10275","title":"TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation","created":"2024-12-13","cited_by_count":7,"area":null},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2204.06558","title":"Controllable Video Generation through Global and Local Motion Dynamics","created":"2022-04-13","cited_by_count":6,"area":null},{"id":"2207.10833","title":"Few-shot Image Generation Using Discrete Content Representation","created":"2022-07-22","cited_by_count":6,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2303.18013","title":"LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2401.02838","title":"CrisisViT: A Robust Vision Transformer for Crisis Image Classification","created":"2024-01-05","cited_by_count":5,"area":null},{"id":"2403.13850","title":"Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2205.00001","title":"Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2210.01249","title":"LOPR: Latent Occupancy PRediction using Generative Models","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2212.14376","title":"Long-horizon video prediction using a dynamic latent hierarchy","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2507.04667","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2606.09156","title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2106.02719","title":"Hierarchical Video Generation for Complex Data","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2106.05658","title":"Conditional COT-GAN for Video Prediction with Kernel Smoothing","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2304.07483","title":"Video Generation Beyond a Single Clip","created":"2023-04-15","cited_by_count":3,"area":null},{"id":"2308.10441","title":"X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events","created":"2023-08-21","cited_by_count":3,"area":null}],"next_cursor":"100"}