{"total":265,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"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":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"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":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"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":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2106.03844","title":"Mean-Shifted Contrastive Loss for Anomaly Detection","created":"2021-06-07","cited_by_count":88,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2103.17263","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","created":"2021-03-31","cited_by_count":81,"area":null},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2106.04185","title":"LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization","created":"2021-06-08","cited_by_count":67,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2103.02243","title":"MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions","created":"2021-03-03","cited_by_count":54,"area":null},{"id":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54,"area":null},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"area":null},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49,"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":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39,"area":null},{"id":"2102.10271","title":"Meta-Learning Dynamics Forecasting Using Task Inference","created":"2021-02-20","cited_by_count":38,"area":null},{"id":"2103.13716","title":"Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting","created":"2021-03-25","cited_by_count":38,"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":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35,"area":null},{"id":"2104.10066","title":"EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task","created":"2021-04-16","cited_by_count":34,"area":null},{"id":"2103.04192","title":"High Perceptual Quality Image Denoising with a Posterior Sampling CGAN","created":"2021-03-06","cited_by_count":33,"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":"2203.16084","title":"STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction","created":"2022-03-30","cited_by_count":31,"area":null},{"id":"2103.15295","title":"Best-Buddy GANs for Highly Detailed Image Super-Resolution","created":"2021-03-29","cited_by_count":30,"area":null},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2207.10948","title":"Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection","created":"2022-07-22","cited_by_count":27,"area":null},{"id":"2110.09768","title":"Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23,"area":null},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2207.06167","title":"Unsupervised Visual Representation Learning by Synchronous Momentum Grouping","created":"2022-07-13","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":"2107.03120","title":"Cross-View Exocentric to Egocentric Video Synthesis","created":"2021-07-07","cited_by_count":20,"area":null},{"id":"2212.07010","title":"Cross-Domain Video Anomaly Detection without Target Domain Adaptation","created":"2022-12-14","cited_by_count":20,"area":null},{"id":"2103.09439","title":"HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks","created":"2021-03-17","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":"2405.19387","title":"Video Anomaly Detection in 10 Years: A Survey and Outlook","created":"2024-05-29","cited_by_count":18,"area":null},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2107.04619","title":"Diverse Video Generation using a Gaussian Process Trigger","created":"2021-07-09","cited_by_count":17,"area":null},{"id":"2203.15836","title":"VPTR: Efficient Transformers for Video Prediction","created":"2022-03-29","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":"2103.14616","title":"Training a Task-Specific Image Reconstruction Loss","created":"2021-03-26","cited_by_count":16,"area":null},{"id":"2104.09498","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","created":"2021-04-19","cited_by_count":16,"area":null},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","cited_by_count":16,"area":null},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16,"area":null},{"id":"2210.10773","title":"Anomaly Detection Requires Better Representations","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2412.10925","title":"Video Representation Learning with Joint-Embedding Predictive Architectures","created":"2024-12-14","cited_by_count":15,"area":null},{"id":"2106.11160","title":"Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics","created":"2021-06-21","cited_by_count":14,"area":null},{"id":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2102.12033","title":"Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks","created":"2021-02-24","cited_by_count":13,"area":null},{"id":"2110.01442","title":"A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing","created":"2021-10-01","cited_by_count":13,"area":null},{"id":"2207.01390","title":"FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy","created":"2022-07-04","cited_by_count":13,"area":null},{"id":"2211.08944","title":"Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality","created":"2022-11-16","cited_by_count":13,"area":null},{"id":"2312.12917","title":"Sign Language Production with Latent Motion Transformer","created":"2023-12-20","cited_by_count":13,"area":null},{"id":"2404.00485","title":"DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans","created":"2024-03-30","cited_by_count":13,"area":null},{"id":"2107.01619","title":"Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects","created":"2021-07-04","cited_by_count":12,"area":null},{"id":"2202.00997","title":"Gradient Variance Loss for Structure-Enhanced Image Super-Resolution","created":"2022-02-02","cited_by_count":12,"area":null},{"id":"2212.06026","title":"Video Prediction by Efficient Transformers","created":"2022-12-12","cited_by_count":12,"area":null},{"id":"2512.05115","title":"Light-X: Generative 4D Video Rendering with Camera and Illumination Control","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2104.14764","title":"CoCon: Cooperative-Contrastive Learning","created":"2021-04-30","cited_by_count":11,"area":null},{"id":"2108.08815","title":"Click to Move: Controlling Video Generation with Sparse Motion","created":"2021-08-19","cited_by_count":11,"area":null},{"id":"2206.02241","title":"A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarX","created":"2022-06-05","cited_by_count":11,"area":null},{"id":"2302.11101","title":"Learning from Predictions: Fusing Training and Autoregressive Inference for Long-Term Spatiotemporal Forecasts","created":"2023-02-22","cited_by_count":11,"area":null},{"id":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2104.01517","title":"PDWN: Pyramid Deformable Warping Network for Video Interpolation","created":"2021-04-04","cited_by_count":10,"area":null},{"id":"2109.13076","title":"Using neural networks to solve the 2D Poisson equation for electric field computation in plasma fluid simulations","created":"2021-09-27","cited_by_count":10,"area":null},{"id":"2111.03649","title":"Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution","created":"2021-11-05","cited_by_count":10,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2210.01559","title":"Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2108.05658","title":"Conditional Temporal Variational AutoEncoder for Action Video Prediction","created":"2021-08-12","cited_by_count":9,"area":null},{"id":"2201.04898","title":"Flexible Style Image Super-Resolution using Conditional Objective","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2305.12333","title":"GRACE: Loss-Resilient Real-Time Video through Neural Codecs","created":"2023-05-21","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":"2506.01061","title":"AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation","created":"2025-06-01","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}],"next_cursor":"100"}